Search

Observing that the key for robotic action planning is to understand the target-object motion when its associated part is manipulated by the end effector, we propose to generate the 3D object-part scene flow and extract its transformations to solve the action trajectories for diverse embodiments. The advantage of our approach is that it derives the robot action explicitly from object motion prediction, yielding a more robust policy by understanding the object motions. Also, beyond policies trained on embodiment-centric data, our method is embodiment-agnostic, generalizable across diverse embodiments, and being able to learn from human demonstrations. Our method comprises three components: an object-part predictor to locate the part for the end effector to manipulate, an RGBD video generator to predict future RGBD videos, and a trajectory planner to extract embodiment-agnostic transformation sequences and solve the trajectory for diverse embodiments. Trained on videos even without trajectory data, our method still outperforms existing works significantly by 27.7% and 26.2% on the prevailing virtual environments MetaWorld and Franka-Kitchen, respectively. Furthermore, we conducted real-world experiments, showing that our policy, trained only with human demonstration, can be deployed to various embodiments., Comment: 8 pages, 7 figures

This technical report outlines our submission system for the CHiME-8 NOTSOFAR-1 Challenge. The primary difficulty of this challenge is the dataset recorded across various conference rooms, which captures real-world complexities such as high overlap rates, background noises, a variable number of speakers, and natural conversation styles. To address these issues, we optimized the system in several aspects: For front-end speech signal processing, we introduced a data-driven joint training method for diarization and separation (JDS) to enhance audio quality. Additionally, we also integrated traditional guided source separation (GSS) for multi-channel track to provide complementary information for the JDS. For back-end speech recognition, we enhanced Whisper with WavLM, ConvNeXt, and Transformer innovations, applying multi-task training and Noise KLD augmentation, to significantly advance ASR robustness and accuracy. Our system attained a Time-Constrained minimum Permutation Word Error Rate (tcpWER) of 14.265% and 22.989% on the CHiME-8 NOTSOFAR-1 Dev-set-2 multi-channel and single-channel tracks, respectively.

Recently, Handwritten Mathematical Expression Recognition (HMER) has gained considerable attention in pattern recognition for its diverse applications in document understanding. Current methods typically approach HMER as an image-to-sequence generation task within an autoregressive (AR) encoder-decoder framework. However, these approaches suffer from several drawbacks: 1) a lack of overall language context, limiting information utilization beyond the current decoding step; 2) error accumulation during AR decoding; and 3) slow decoding speed. To tackle these problems, this paper makes the first attempt to build a novel bottom-up Non-AutoRegressive Modeling approach for HMER, called NAMER. NAMER comprises a Visual Aware Tokenizer (VAT) and a Parallel Graph Decoder (PGD). Initially, the VAT tokenizes visible symbols and local relations at a coarse level. Subsequently, the PGD refines all tokens and establishes connectivities in parallel, leveraging comprehensive visual and linguistic contexts. Experiments on CROHME 2014/2016/2019 and HME100K datasets demonstrate that NAMER not only outperforms the current state-of-the-art (SOTA) methods on ExpRate by 1.93%/2.35%/1.49%/0.62%, but also achieves significant speedups of 13.7x and 6.7x faster in decoding time and overall FPS, proving the effectiveness and efficiency of NAMER., Comment: Accepted by ECCV 2024

Enabling robotic agents to perform complex long-horizon tasks has been a long-standing goal in robotics and artificial intelligence (AI). Despite the potential shown by large language models (LLMs), their planning capabilities remain limited to short-horizon tasks and they are unable to replace the symbolic planning approach. Symbolic planners, on the other hand, may encounter execution errors due to their common assumption of complete domain knowledge which is hard to manually prepare for an open-world setting. In this paper, we introduce a Language-Augmented Symbolic Planner (LASP) that integrates pre-trained LLMs to enable conventional symbolic planners to operate in an open-world environment where only incomplete knowledge of action preconditions, objects, and properties is initially available. In case of execution errors, LASP can utilize the LLM to diagnose the cause of the error based on the observation and interact with the environment to incrementally build up its knowledge base necessary for accomplishing the given tasks. Experiments demonstrate that LASP is proficient in solving planning problems in the open-world setting, performing well even in situations where there are multiple gaps in the knowledge., Comment: Accepted by Robotics: Science and Systems (RSS) 2024

Fabric manipulation dynamically is commonly seen in manufacturing and domestic settings. While dynamically manipulating a fabric piece to reach a target state is highly efficient, this task presents considerable challenges due to the varying properties of different fabrics, complex dynamics when interacting with environments, and meeting required goal conditions. To address these challenges, we present \textit{One Fling to Goal}, an algorithm capable of handling fabric pieces with diverse shapes and physical properties across various scenarios. Our method learns a graph-based dynamics model equipped with environmental awareness. With this dynamics model, we devise a real-time controller to enable high-speed fabric manipulation in one attempt, requiring less than 3 seconds to finish the goal-conditioned task. We experimentally validate our method on a goal-conditioned manipulation task in five diverse scenarios. Our method significantly improves this goal-conditioned task, achieving an average error of 13.2mm in complex scenarios. Our method can be seamlessly transferred to real-world robotic systems and generalized to unseen scenarios in a zero-shot manner.

Bimanual manipulation tasks typically involve multiple stages which require efficient interactions between two arms, posing step-wise and stage-wise challenges for imitation learning systems. Specifically, failure and delay of one step will broadcast through time, hinder success and efficiency of each sub-stage task, and thereby overall task performance. Although recent works have made strides in addressing certain challenges, few approaches explicitly consider the multi-stage nature of bimanual tasks while simultaneously emphasizing the importance of inference speed. In this paper, we introduce a novel keypose-conditioned consistency policy tailored for bimanual manipulation. It is a hierarchical imitation learning framework that consists of a high-level keypose predictor and a low-level trajectory generator. The predicted keyposes provide guidance for trajectory generation and also mark the completion of one sub-stage task. The trajectory generator is designed as a consistency model trained from scratch without distillation, which generates action sequences conditioning on current observations and predicted keyposes with fast inference speed. Simulated and real-world experimental results demonstrate that the proposed approach surpasses baseline methods in terms of success rate and operational efficiency. Codes are available at https://github.com/ManUtdMoon/BiKC., Comment: Accepted by The 16th International Workshop on the Algorithmic Foundations of Robotics (WAFR 2024)

Analyzing time series of fluxes from stars, known as stellar light curves, can reveal valuable information about stellar properties. However, most current methods rely on extracting summary statistics, and studies using deep learning have been limited to supervised approaches. In this research, we investigate the scaling law properties that emerge when learning from astronomical time series data using self-supervised techniques. By employing the GPT-2 architecture, we show the learned representation improves as the number of parameters increases from $10^4$ to $10^9$, with no signs of performance plateauing. We demonstrate that a self-supervised Transformer model achieves 3-10 times the sample efficiency compared to the state-of-the-art supervised learning model when inferring the surface gravity of stars as a downstream task. Our research lays the groundwork for analyzing stellar light curves by examining them through large-scale auto-regressive generative models., Comment: 11 pages, 5 figures, ICML 2024 AI4Science workshop

In this paper, we propose a variance-preserving interpolation framework to improve diffusion models for single-channel speech enhancement (SE) and automatic speech recognition (ASR). This new variance-preserving interpolation diffusion model (VPIDM) approach requires only 25 iterative steps and obviates the need for a corrector, an essential element in the existing variance-exploding interpolation diffusion model (VEIDM). Two notable distinctions between VPIDM and VEIDM are the scaling function of the mean of state variables and the constraint imposed on the variance relative to the mean's scale. We conduct a systematic exploration of the theoretical mechanism underlying VPIDM and develop insights regarding VPIDM's applications in SE and ASR using VPIDM as a frontend. Our proposed approach, evaluated on two distinct data sets, demonstrates VPIDM's superior performances over conventional discriminative SE algorithms. Furthermore, we assess the performance of the proposed model under varying signal-to-noise ratio (SNR) levels. The investigation reveals VPIDM's improved robustness in target noise elimination when compared to VEIDM. Furthermore, utilizing the mid-outputs of both VPIDM and VEIDM results in enhanced ASR accuracies, thereby highlighting the practical efficacy of our proposed approach.

Despite recent advancements in speech generation with text prompt providing control over speech style, voice attributes in synthesized speech remain elusive and challenging to control. This paper introduces a novel task: voice attribute editing with text prompt, with the goal of making relative modifications to voice attributes according to the actions described in the text prompt. To solve this task, VoxEditor, an end-to-end generative model, is proposed. In VoxEditor, addressing the insufficiency of text prompt, a Residual Memory (ResMem) block is designed, that efficiently maps voice attributes and these descriptors into the shared feature space. Additionally, the ResMem block is enhanced with a voice attribute degree prediction (VADP) block to align voice attributes with corresponding descriptors, addressing the imprecision of text prompt caused by non-quantitative descriptions of voice attributes. We also establish the open-source VCTK-RVA dataset, which leads the way in manual annotations detailing voice characteristic differences among different speakers. Extensive experiments demonstrate the effectiveness and generalizability of our proposed method in terms of both objective and subjective metrics. The dataset and audio samples are available on the website.

In robotic insertion tasks where the uncertainty exceeds the allowable tolerance, a good search strategy is essential for successful insertion and significantly influences efficiency. The commonly used blind search method is time-consuming and does not exploit the rich contact information. In this paper, we propose a novel search strategy that actively utilizes the information contained in the contact configuration and shows high efficiency. In particular, we formulate this problem as a Partially Observable Markov Decision Process (POMDP) with carefully designed primitives based on an in-depth analysis of the contact configuration's static stability. From the formulated POMDP, we can derive a novel search strategy. Thanks to its simplicity, this search strategy can be incorporated into a Finite-State-Machine (FSM) controller. The behaviors of the FSM controller are realized through a low-level Cartesian Impedance Controller. Our method is based purely on the robot's proprioceptive sensing and does not need visual or tactile sensors. To evaluate the effectiveness of our proposed strategy and control framework, we conduct extensive comparison experiments in simulation, where we compare our method with the baseline approach. The results demonstrate that our proposed method achieves a higher success rate with a shorter search time and search trajectory length compared to the baseline method. Additionally, we show that our method is robust to various initial displacement errors.

Microscopic traffic simulation plays a crucial role in transportation engineering by providing insights into individual vehicle behavior and overall traffic flow. However, creating a realistic simulator that accurately replicates human driving behaviors in various traffic conditions presents significant challenges. Traditional simulators relying on heuristic models often fail to deliver accurate simulations due to the complexity of real-world traffic environments. Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations. In this paper, we propose a novel approach called learner-aware supervised imitation learning to address the covariate shift problem in multi-agent imitation learning. By leveraging a variational autoencoder simultaneously modeling the expert and learner state distribution, our approach augments expert states such that the augmented state is aware of learner state distribution. Our method, applied to urban traffic simulation, demonstrates significant improvements over existing state-of-the-art baselines in both short-term microscopic and long-term macroscopic realism when evaluated on the real-world dataset pNEUMA., Comment: Accepted by CVPR 2024. arXiv admin note: text overlap with arXiv:2306.06401

The management of mixed traffic that consists of robot vehicles (RVs) and human-driven vehicles (HVs) at complex intersections presents a multifaceted challenge. Traditional signal controls often struggle to adapt to dynamic traffic conditions and heterogeneous vehicle types. Recent advancements have turned to strategies based on reinforcement learning (RL), leveraging its model-free nature, real-time operation, and generalizability over different scenarios. We introduce a hierarchical RL framework to manage mixed traffic through precise longitudinal and lateral control of RVs. Our proposed hierarchical framework combines the state-of-the-art mixed traffic control algorithm as a high level decision maker to improve the performance and robustness of the whole system. Our experiments demonstrate that the framework can reduce the average waiting time by up to 54% compared to the state-of-the-art mixed traffic control method. When the RV penetration rate exceeds 60%, our technique consistently outperforms conventional traffic signal control programs in terms of the average waiting time for all vehicles at the intersection.

The complex dynamicity of open-world objects presents non-negligible challenges for multi-object tracking (MOT), often manifested as severe deformations, fast motion, and occlusions. Most methods that solely depend on coarse-grained object cues, such as boxes and the overall appearance of the object, are susceptible to degradation due to distorted internal relationships of dynamic objects. To address this problem, this work proposes NetTrack, an efficient, generic, and affordable tracking framework to introduce fine-grained learning that is robust to dynamicity. Specifically, NetTrack constructs a dynamicity-aware association with a fine-grained Net, leveraging point-level visual cues. Correspondingly, a fine-grained sampler and matching method have been incorporated. Furthermore, NetTrack learns object-text correspondence for fine-grained localization. To evaluate MOT in extremely dynamic open-world scenarios, a bird flock tracking (BFT) dataset is constructed, which exhibits high dynamicity with diverse species and open-world scenarios. Comprehensive evaluation on BFT validates the effectiveness of fine-grained learning on object dynamicity, and thorough transfer experiments on challenging open-world benchmarks, i.e., TAO, TAO-OW, AnimalTrack, and GMOT-40, validate the strong generalization ability of NetTrack even without finetuning. Project page: https://george-zhuang.github.io/nettrack/., Comment: Accepted by CVPR 2024

Bagging operations, common in packaging and assisted living applications, are challenging due to a bag's complex deformable properties. To address this, we develop a robotic system for automated bagging tasks using an adaptive structure-of-interest (SOI) manipulation approach. Our method relies on real-time visual feedback to dynamically adjust manipulation without requiring prior knowledge of bag materials or dynamics. We present a robust pipeline featuring state estimation for SOIs using Gaussian Mixture Models (GMM), SOI generation via optimization-based bagging techniques, SOI motion planning with Constrained Bidirectional Rapidly-exploring Random Trees (CBiRRT), and dual-arm manipulation coordinated by Model Predictive Control (MPC). Experiments demonstrate the system's ability to achieve precise, stable bagging of various objects using adaptive coordination of the manipulators. The proposed framework advances the capability of dual-arm robots to perform more sophisticated automation of common tasks involving interactions with deformable objects.

Navigating a nonholonomic robot in a cluttered environment requires extremely accurate perception and locomotion for collision avoidance. This paper presents NeuPAN: a real-time, highly-accurate, map-free, robot-agnostic, and environment-invariant robot navigation solution. Leveraging a tightly-coupled perception-locomotion framework, NeuPAN has two key innovations compared to existing approaches: 1) it directly maps raw points to a learned multi-frame distance space, avoiding error propagation from perception to control; 2) it is interpretable from an end-to-end model-based learning perspective, enabling provable convergence. The crux of NeuPAN is to solve a high-dimensional end-to-end mathematical model with various point-level constraints using the plug-and-play (PnP) proximal alternating-minimization network (PAN) with neurons in the loop. This allows NeuPAN to generate real-time, end-to-end, physically-interpretable motions directly from point clouds, which seamlessly integrates data- and knowledge-engines, where its network parameters are adjusted via back propagation. We evaluate NeuPAN on car-like robot, wheel-legged robot, and passenger autonomous vehicle, in both simulated and real-world environments. Experiments demonstrate that NeuPAN outperforms various benchmarks, in terms of accuracy, efficiency, robustness, and generalization capability across various environments, including the cluttered sandbox, office, corridor, and parking lot. We show that NeuPAN works well in unstructured environments with arbitrary-shape undetectable objects, making impassable ways passable., Comment: submit to TRO

Cable-driven parallel robots (CDPRs) have gained significant attention due to their promising advantages. When deploying CDPRs in practice, the kinematic modeling is a key question. Unlike serial robots, CDPRs have a simple inverse kinematics problem but a complex forward kinematics (FK) issue. So, the development of accurate and efficient FK solvers has been a prominent research focus in CDPR applications. By observing the topology within CDPRs, in this paper, we propose a graph-based representation to model CDPRs and introduce CafkNet, a fast and general FK solving method, leveraging Graph Neural Network (GNN) to learn the topological structure and yield the real FK solutions with superior generality, high accuracy, and low time cost. CafkNet is extensively tested on 3D and 2D CDPRs in different configurations, both in simulators and real scenarios. The results demonstrate its ability to learn CDPRs' internal topology and accurately solve the FK problem. Then, the zero-shot generalization from one configuration to another is validated. Also, the sim2real gap can be bridged by CafkNet using both simulation and real-world data. To the best of our knowledge, it is the first study that employs the GNN to solve the FK problem for CDPRs., Comment: To the best of our knowledge, it is the first study to employ the GNN for the FK problem of CDPRs. The first two authors have equal contributions. Videos and codes are available at https://sites.google.com/view/cafknet/site

Bimodal objects, such as the checkerboard pattern used in camera calibration, markers for object tracking, and text on road signs, to name a few, are prevalent in our daily lives and serve as a visual form to embed information that can be easily recognized by vision systems. While binarization from intensity images is crucial for extracting the embedded information in the bimodal objects, few previous works consider the task of binarization of blurry images due to the relative motion between the vision sensor and the environment. The blurry images can result in a loss in the binarization quality and thus degrade the downstream applications where the vision system is in motion. Recently, neuromorphic cameras offer new capabilities for alleviating motion blur, but it is non-trivial to first deblur and then binarize the images in a real-time manner. In this work, we propose an event-based binary reconstruction method that leverages the prior knowledge of the bimodal target's properties to perform inference independently in both event space and image space and merge the results from both domains to generate a sharp binary image. We also develop an efficient integration method to propagate this binary image to high frame rate binary video. Finally, we develop a novel method to naturally fuse events and images for unsupervised threshold identification. The proposed method is evaluated in publicly available and our collected data sequence, and shows the proposed method can outperform the SOTA methods to generate high frame rate binary video in real-time on CPU-only devices., Comment: NA

The manipulation of deformable objects by robotic systems presents a significant challenge due to their complex and infinite-dimensional configuration spaces. This paper introduces a novel approach to Deformable Object Manipulation (DOM) by emphasizing the identification and manipulation of Structures of Interest (SOIs) in deformable fabric bags. We propose a bimanual manipulation framework that leverages a Graph Neural Network (GNN)-based latent dynamics model to succinctly represent and predict the behavior of these SOIs. Our approach involves constructing a graph representation from partial point cloud data of the object and learning the latent dynamics model that effectively captures the essential deformations of the fabric bag within a reduced computational space. By integrating this latent dynamics model with Model Predictive Control (MPC), we empower robotic manipulators to perform precise and stable manipulation tasks focused on the SOIs. We have validated our framework through various empirical experiments demonstrating its efficacy in bimanual manipulation of fabric bags. Our contributions not only address the complexities inherent in DOM but also provide new perspectives and methodologies for enhancing robotic interactions with deformable objects by concentrating on their critical structural elements. Experimental videos can be obtained from https://sites.google.com/view/bagbot.

We present a novel unified framework that concurrently tackles recognition and future prediction for human hand pose and action modeling. Previous works generally provide isolated solutions for either recognition or prediction, which not only increases the complexity of integration in practical applications, but more importantly, cannot exploit the synergy of both sides and suffer suboptimal performances in their respective domains. To address this problem, we propose a generative Transformer VAE architecture to model hand pose and action, where the encoder and decoder capture recognition and prediction respectively, and their connection through the VAE bottleneck mandates the learning of consistent hand motion from the past to the future and vice versa. Furthermore, to faithfully model the semantic dependency and different temporal granularity of hand pose and action, we decompose the framework into two cascaded VAE blocks: the first and latter blocks respectively model the short-span poses and long-span action, and are connected by a mid-level feature representing a sub-second series of hand poses. This decomposition into block cascades facilitates capturing both short-term and long-term temporal regularity in pose and action modeling, and enables training two blocks separately to fully utilize datasets with annotations of different temporal granularities. We train and evaluate our framework across multiple datasets; results show that our joint modeling of recognition and prediction improves over isolated solutions, and that our semantic and temporal hierarchy facilitates long-term pose and action modeling., Comment: Accepted by ECCV HANDS Workshop 2024

Greenhouse gas emissions have dramatically risen since the early 1900s with U.S. transportation generating 28% of U.S. emissions. As such, there is interest in reducing transportation-related emissions. Specifically, sustainability research has sprouted around signalized intersections as intersections allow different streams of traffic to cross and change directions. Recent research has developed mixed traffic control eco-driving strategies at signalized intersections to decrease emissions. However, the inherent structure of a signalized intersection generates increased emissions by creating frequent acceleration/deceleration events, excessive idling from traffic congestion, and stop-and-go waves. Thus, we believe unsignalized intersections hold potential for further sustainability improvements. In this work, we provide an emissions analysis on unsignalized intersections with complex, real-world topologies and traffic demands where mixed traffic control strategies are employed by robot vehicles (RVs) to reduce wait times and congestion. We find with at least 10% RV penetration rate, RVs generate less fuel consumption, CO2 emissions, and NOx emissions than signalized intersections by up to 27%, 27% and 28%, respectively. With at least 30% RVs, CO and HC emissions are reduced by up to 42% and 43%, respectively. Additionally, RVs can reduce network-wide emissions despite only employing their strategies at intersections., Comment: Accepted to 4th IEEE Forum for Innovative Sustainable Transportation Systems

Controlling and coordinating urban traffic flow through robot vehicles is emerging as a novel transportation paradigm for the future. While this approach garners growing attention from researchers and practitioners, effectively managing and coordinating large-scale mixed traffic remains a challenge. We introduce an effective framework for large-scale mixed traffic control via privacy-preserving crowdsourcing and dynamic vehicle routing. Our framework consists of three modules: a privacy-protecting crowdsensing method, a graph propagation-based traffic forecasting method, and a privacy-preserving route selection mechanism. We evaluate our framework using a real-world road network. The results show that our framework accurately forecasts traffic flow, efficiently mitigates network-wide RV shortage issue, and coordinates large-scale mixed traffic. Compared to other baseline methods, our framework not only reduces the RV shortage issue up to 69.4% but also reduces the average waiting time of all vehicles in the network up to 27%., Comment: Accepted to IEEE Internet of Things Journal

This paper studies the design, control, and learning of a novel robotic limb that produces overconstrained locomotion by employing the Bennett linkage for motion generation, capable of parametric reconfiguration between a reptile- and mammal-inspired morphology within a single quadruped. In contrast to the prevailing focus on planar linkages, this research delves into adopting overconstrained linkages as the limb mechanism. The overconstrained linkages have solid theoretical foundations in advanced kinematics but are under-explored in robotic applications. This study showcases the morphological superiority of Overconstrained Robotic Limbs (ORLs) that can transform into planar or spherical limbs, exemplified using the simplest case of a Bennett linkage as an ORL. We apply Model Predictive Control (MPC) to simulate a range of overconstrained locomotion tasks, revealing its superiority in energy efficiency against planar limbs when considering foothold distances and speeds. The results are further verified in overconstrained locomotion policies optimized from Reinforcement Learning (RL). From an evolutionary biology perspective, these findings highlight the mechanism distinctions in limb design between reptiles and mammals and represent the first documented instance of ORLs outperforming planar limb designs in dynamic locomotion. Future studies will focus on deploying the model-based and learning-based overconstrained locomotion skills in the robotic hardware to close the Sim2Real gap for developing evolutionary-inspired, energy-efficient control of novel robotic limbs., Comment: 30 pages, 20 figures, 2 tables

The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of vision-and-language navigation (VLN), it is equally interesting to know what information the models utilize for their decision-making in the navigation tasks. To understand the inner workings of deep neural models, various explanation methods have been developed for promoting explainable AI (XAI). But they are mostly applied to deep neural models for image or text classification tasks and little work has been done in explaining deep neural models for VLN tasks. In this paper, we address these problems by building quantitative benchmarks to evaluate explanation methods for VLN models in terms of faithfulness. We propose a new erasure-based evaluation pipeline to measure the step-wise textual explanation in the sequential decision-making setting. We evaluate several explanation methods for two representative VLN models on two popular VLN datasets and reveal valuable findings through our experiments., Comment: Accepted by ECAI 2023

Amidst the swift advancements in photography and sensor technologies, high-definition cameras have become commonplace in the deployment of Unmanned Aerial Vehicles (UAVs) for diverse operational purposes. Within the domain of UAV imagery analysis, the segmentation of ultra-high resolution images emerges as a substantial and intricate challenge, especially when grappling with the constraints imposed by GPU memory-restricted computational devices. This paper delves into the intricate problem of achieving efficient and effective segmentation of ultra-high resolution UAV imagery, while operating under stringent GPU memory limitation. The strategy of existing approaches is to downscale the images to achieve computationally efficient segmentation. However, this strategy tends to overlook smaller, thinner, and curvilinear regions. To address this problem, we propose a GPU memory-efficient and effective framework for local inference without accessing the context beyond local patches. In particular, we introduce a novel spatial-guided high-resolution query module, which predicts pixel-wise segmentation results with high quality only by querying nearest latent embeddings with the guidance of high-resolution information. Additionally, we present an efficient memory-based interaction scheme to correct potential semantic bias of the underlying high-resolution information by associating cross-image contextual semantics. For evaluation of our approach, we perform comprehensive experiments over public benchmarks and achieve superior performance under both conditions of small and large GPU memory usage limitations. We will release the model and codes in the future.

Event-based cameras are increasingly utilized in various applications, owing to their high temporal resolution and low power consumption. However, a fundamental challenge arises when deploying multiple such cameras: they operate on independent time systems, leading to temporal misalignment. This misalignment can significantly degrade performance in downstream applications. Traditional solutions, which often rely on hardware-based synchronization, face limitations in compatibility and are impractical for long-distance setups. To address these challenges, we propose a novel algorithm that exploits the motion of objects in the shared field of view to achieve millisecond-level synchronization among multiple event-based cameras. Our method also concurrently estimates extrinsic parameters. We validate our approach in both simulated and real-world indoor/outdoor scenarios, demonstrating successful synchronization and accurate extrinsic parameters estimation.

Stellar light curves contain valuable information about oscillations and granulation, offering insights into stars' internal structures and evolutionary states. Traditional asteroseismic techniques, primarily focused on power spectral analysis, often overlook the crucial phase information in these light curves. Addressing this gap, recent machine learning applications, particularly those using Convolutional Neural Networks (CNNs), have made strides in inferring stellar properties from light curves. However, CNNs are limited by their localized feature extraction capabilities. In response, we introduce $\textit{Astroconformer}$, a Transformer-based deep learning framework, specifically designed to capture long-range dependencies in stellar light curves. Our empirical analysis centers on estimating surface gravity ($\log g$), using a dataset derived from single-quarter Kepler light curves with $\log g$ values ranging from 0.2 to 4.4. $\textit{Astroconformer}$ demonstrates superior performance, achieving a root-mean-square-error (RMSE) of 0.017 dex at $\log g\approx3$ in data-rich regimes and up to 0.1 dex in sparser areas. This performance surpasses both K-nearest neighbor models and advanced CNNs. Ablation studies highlight the influence of receptive field size on model effectiveness, with larger fields correlating to improved results. $\textit{Astroconformer}$ also excels in extracting $\nu_{\max}$ with high precision. It achieves less than 2% relative median absolute error for 90-day red giant light curves. Notably, the error remains under 3% for 30-day light curves, whose oscillations are undetectable by a conventional pipeline in 30% cases. Furthermore, the attention mechanisms in $\textit{Astroconformer}$ align closely with the characteristics of stellar oscillations and granulation observed in light curves., Comment: 15 pages, 10 figures, Accepted by MNRAS

Previous Multimodal Information based Speech Processing (MISP) challenges mainly focused on audio-visual speech recognition (AVSR) with commendable success. However, the most advanced back-end recognition systems often hit performance limits due to the complex acoustic environments. This has prompted a shift in focus towards the Audio-Visual Target Speaker Extraction (AVTSE) task for the MISP 2023 challenge in ICASSP 2024 Signal Processing Grand Challenges. Unlike existing audio-visual speech enhance-ment challenges primarily focused on simulation data, the MISP 2023 challenge uniquely explores how front-end speech processing, combined with visual clues, impacts back-end tasks in real-world scenarios. This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the ac-curacy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments. This paper delivers a thorough overview of the task setting, dataset, and baseline system of the MISP 2023 challenge. It also includes an in-depth analysis of the challenges participants may encounter. The experimental results highlight the demanding nature of this task, and we look forward to the innovative solutions participants will bring forward., Comment: 5 pages, 4 figures

This technical report details our submission system to the CHiME-7 DASR Challenge, which focuses on speaker diarization and speech recognition under complex multi-speaker scenarios. Additionally, it also evaluates the efficiency of systems in handling diverse array devices. To address these issues, we implemented an end-to-end speaker diarization system and introduced a rectification strategy based on multi-channel spatial information. This approach significantly diminished the word error rates (WER). In terms of recognition, we utilized publicly available pre-trained models as the foundational models to train our end-to-end speech recognition models. Our system attained a Macro-averaged diarization-attributed WER (DA-WER) of 21.01% on the CHiME-7 evaluation set, which signifies a relative improvement of 62.04% over the official baseline system., Comment: Accepted by 2023 CHiME Workshop, Oral

Robotic bin packing is very challenging, especially when considering practical needs such as object variety and packing compactness. This paper presents SDF-Pack, a new approach based on signed distance field (SDF) to model the geometric condition of objects in a container and compute the object placement locations and packing orders for achieving a more compact bin packing. Our method adopts a truncated SDF representation to localize the computation, and based on it, we formulate the SDF minimization heuristic to find optimized placements to compactly pack objects with the existing ones. To further improve space utilization, if the packing sequence is controllable, our method can suggest which object to be packed next. Experimental results on a large variety of everyday objects show that our method can consistently achieve higher packing compactness over 1,000 packing cases, enabling us to pack more objects into the container, compared with the existing heuristics under various packing settings.

Proximity sensing detects an object's presence without contact. However, research has rarely explored proximity sensing in granular materials (GM) due to GM's lack of visual and complex properties. In this paper, we propose a granular-material-embedded autonomous proximity sensing system (GRAINS) based on three granular phenomena (fluidization, jamming, and failure wedge zone). GRAINS can automatically sense buried objects beneath GM in real-time manner (at least ~20 hertz) and perceive them 0.5 ~ 7 centimeters ahead in different granules without the use of vision or touch. We introduce a new spiral trajectory for the probe raking in GM, combining linear and circular motions, inspired by a common granular fluidization technique. Based on the observation of force-raising when granular jamming occurs in the failure wedge zone in front of the probe during its raking, we employ Gaussian process regression to constantly learn and predict the force patterns and detect the force anomaly resulting from granular jamming to identify the proximity sensing of buried objects. Finally, we apply GRAINS to a Bayesian-optimization-algorithm-guided exploration strategy to successfully localize underground objects and outline their distribution using proximity sensing without contact or digging. This work offers a simple yet reliable method with potential for safe operation in building habitation infrastructure on an alien planet without human intervention., Comment: 35 pages, 5 figures,2 tables. Videos available at https://sites.google.com/view/grains2/home

Domain adaptation (DA) has demonstrated significant promise for real-time nighttime unmanned aerial vehicle (UAV) tracking. However, the state-of-the-art (SOTA) DA still lacks the potential object with accurate pixel-level location and boundary to generate the high-quality target domain training sample. This key issue constrains the transfer learning of the real-time daytime SOTA trackers for challenging nighttime UAV tracking. Recently, the notable Segment Anything Model (SAM) has achieved a remarkable zero-shot generalization ability to discover abundant potential objects due to its huge data-driven training approach. To solve the aforementioned issue, this work proposes a novel SAM-powered DA framework for real-time nighttime UAV tracking, i.e., SAM-DA. Specifically, an innovative SAM-powered target domain training sample swelling is designed to determine enormous high-quality target domain training samples from every single raw nighttime image. This novel one-to-many generation significantly expands the high-quality target domain training sample for DA. Comprehensive experiments on extensive nighttime UAV videos prove the robustness and domain adaptability of SAM-DA for nighttime UAV tracking. Especially, compared to the SOTA DA, SAM-DA can achieve better performance with fewer raw nighttime images, i.e., the fewer-better training. This economized training approach facilitates the quick validation and deployment of algorithms for UAVs. The code is available at https://github.com/vision4robotics/SAM-DA.

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure that their hidden and output distributions are consistent, which can be achieved by hierarchical knowledge distillation. However, it is difficult to ensure the distribution consistency simultaneously because the learning of the output distribution depends on the hidden one. In this paper, we propose an adaptive two-stage knowledge distillation method consisting of hidden layer learning and output layer learning. In the former stage, we learn hidden representation with full context by applying mean square error loss function. In the latter stage, we design a power transformation based adaptive smoothness method to learn stable output distribution. It achieved 19\% relative reduction in word error rate, and a faster response for the first token compared with the original streaming model in LibriSpeech corpus.

A realistic long-term microscopic traffic simulator is necessary for understanding how microscopic changes affect traffic patterns at a larger scale. Traditional simulators that model human driving behavior with heuristic rules often fail to achieve accurate simulations due to real-world traffic complexity. To overcome this challenge, researchers have turned to neural networks, which are trained through imitation learning from human driver demonstrations. However, existing learning-based microscopic simulators often fail to generate stable long-term simulations due to the \textit{covariate shift} issue. To address this, we propose a history-masked multi-agent imitation learning method that removes all vehicles' historical trajectory information and applies perturbation to their current positions during learning. We apply our approach specifically to the urban traffic simulation problem and evaluate it on the real-world large-scale pNEUMA dataset, achieving better short-term microscopic and long-term macroscopic similarity to real-world data than state-of-the-art baselines., Comment: update

Photon avalanching nanoparticles (ANPs) exhibit extremely nonlinear upconverted emission valuable for sub-diffraction imaging, nanoscale sensing, and optical computing. Avalanching has been demonstrated with Tm3+, Nd3+ or Pr3+-doped nanocrystals, but their emission is limited to 600 and 800 nm, restricting applications. Here, we utilize Gd3+-assisted energy migration to tune the emission wavelengths of Tm3+-sensitized ANPs and generate highly nonlinear emission of Eu3+, Tb3+, Ho3+, and Er3+ ions. The upconversion intensities of these spectrally discrete ANPs scale with the nonlinearity factor s = 10-17 under 1064 nm excitation at power densities as low as 6 kW/cm2. This strategy for imprinting avalanche behavior on remote emitters can be extended to fluorophores adjacent to ANPs, as we demonstrate with CdS/CdSe/CdS core/shell/shell quantum dots. ANPs with rationally designed energy transfer networks provide the means to transform conventional linear emitters into a highly nonlinear ones, expanding the use of photon avalanching in biological, chemical, and photonic applications., Comment: 13 pages, 5 figures

During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. Here we report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model uses embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and bidirectional blocks with intramodal and intermodal attention to learn a holistic representation of radiographs, the unstructured chief complaint and clinical history, structured clinical information such as laboratory-test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Leveraging unified multimodal Transformer-based models may help streamline triage of patients and facilitate the clinical decision process., Comment: Accepted by Nature Biomedical Engineering

Motion deblurring is a critical ill-posed problem that is important in many vision-based robotics applications. The recently proposed event-based double integral (EDI) provides a theoretical framework for solving the deblurring problem with the event camera and generating clear images at high frame-rate. However, the original EDI is mainly designed for offline computation and does not support real-time requirement in many robotics applications. In this paper, we propose the fast EDI, an efficient implementation of EDI that can achieve real-time online computation on single-core CPU devices, which is common for physical robotic platforms used in practice. In experiments, our method can handle event rates at as high as 13 million event per second in a wide variety of challenging lighting conditions. We demonstrate the benefit on multiple downstream real-time applications, including localization, visual tag detection, and feature matching., Comment: conference ICRA2023 accepted

Calibrating the extrinsic parameters of sensory devices is crucial for fusing multi-modal data. Recently, event cameras have emerged as a promising type of neuromorphic sensors, with many potential applications in fields such as mobile robotics and autonomous driving. When combined with LiDAR, they can provide more comprehensive information about the surrounding environment. Nonetheless, due to the distinctive representation of event cameras compared to traditional frame-based cameras, calibrating them with LiDAR presents a significant challenge. In this paper, we propose a novel method to calibrate the extrinsic parameters between a dyad of an event camera and a LiDAR without the need for a calibration board or other equipment. Our approach takes advantage of the fact that when an event camera is in motion, changes in reflectivity and geometric edges in the environment trigger numerous events, which can also be captured by LiDAR. Our proposed method leverages the edges extracted from events and point clouds and correlates them to estimate extrinsic parameters. Experimental results demonstrate that our proposed method is highly robust and effective in various scenes.

Imitation learning holds great promise for addressing the complex task of autonomous urban driving, as experienced human drivers can navigate highly challenging scenarios with ease. While behavior cloning is a widely used imitation learning approach in autonomous driving due to its exemption from risky online interactions, it suffers from the covariate shift issue. To address this limitation, we propose a context-conditioned imitation learning approach that employs a policy to map the context state into the ego vehicle's future trajectory, rather than relying on the traditional formulation of both ego and context states to predict the ego action. Additionally, to reduce the implicit ego information in the coordinate system, we design an ego-perturbed goal-oriented coordinate system. The origin of this coordinate system is the ego vehicle's position plus a zero mean Gaussian perturbation, and the x-axis direction points towards its goal position. Our experiments on the real-world large-scale Lyft and nuPlan datasets show that our method significantly outperforms state-of-the-art approaches., Comment: Accepted by Robotics: Science and Systems

Despite the increasing prevalence of robots in daily life, their navigation capabilities are still limited to environments with prior knowledge, such as a global map. To fully unlock the potential of robots, it is crucial to enable them to navigate in large-scale unknown and changing unstructured scenarios. This requires the robot to construct an accurate static map in real-time as it explores, while filtering out moving objects to ensure mapping accuracy and, if possible, achieving high-quality pedestrian tracking and collision avoidance. While existing methods can achieve individual goals of spatial mapping or dynamic object detection and tracking, there has been limited research on effectively integrating these two tasks, which are actually coupled and reciprocal. In this work, we propose a solution called S$^2$MAT (Simultaneous and Self-Reinforced Mapping and Tracking) that integrates a front-end dynamic object detection and tracking module with a back-end static mapping module. S$^2$MAT leverages the close and reciprocal interplay between these two modules to efficiently and effectively solve the open problem of simultaneous tracking and mapping in highly dynamic scenarios. We conducted extensive experiments using widely-used datasets and simulations, providing both qualitative and quantitative results to demonstrate S$^2$MAT's state-of-the-art performance in dynamic object detection, tracking, and high-quality static structure mapping. Additionally, we performed long-range robotic navigation in real-world urban scenarios spanning over 7 km, which included challenging obstacles like pedestrians and other traffic agents. The successful navigation provides a comprehensive test of S$^2$MAT's robustness, scalability, efficiency, quality, and its ability to benefit autonomous robots in wild scenarios without pre-built maps., Comment: homepage: https://sites.google.com/view/smat-nav

In this paper, we propose a novel framework for tactile-based dexterous manipulation learning with a blind anthropomorphic robotic hand, i.e. without visual sensing. First, object-related states were extracted from the raw tactile signals by a graph-based perception model - TacGNN. The resulting tactile features were then utilized in the policy learning of an in-hand manipulation task in the second stage. This method was examined by a Baoding ball task - simultaneously manipulating two spheres around each other by 180 degrees in hand. We conducted experiments on object states prediction and in-hand manipulation using a reinforcement learning algorithm (PPO). Results show that TacGNN is effective in predicting object-related states during manipulation by decreasing the RMSE of prediction to 0.096cm comparing to other methods, such as MLP, CNN, and GCN. Finally, the robot hand could finish an in-hand manipulation task solely relying on the robotic own perception - tactile sensing and proprioception. In addition, our methods are tested on three tasks with different difficulty levels and transferred to the real robot without further training., Comment: 8 pages, 4 figures, accepted by RAL

The Multi-modal Information based Speech Processing (MISP) challenge aims to extend the application of signal processing technology in specific scenarios by promoting the research into wake-up words, speaker diarization, speech recognition, and other technologies. The MISP2022 challenge has two tracks: 1) audio-visual speaker diarization (AVSD), aiming to solve ``who spoken when'' using both audio and visual data; 2) a novel audio-visual diarization and recognition (AVDR) task that focuses on addressing ``who spoken what when'' with audio-visual speaker diarization results. Both tracks focus on the Chinese language, and use far-field audio and video in real home-tv scenarios: 2-6 people communicating each other with TV noise in the background. This paper introduces the dataset, track settings, and baselines of the MISP2022 challenge. Our analyses of experiments and examples indicate the good performance of AVDR baseline system, and the potential difficulties in this challenge due to, e.g., the far-field video quality, the presence of TV noise in the background, and the indistinguishable speakers., Comment: 5 pages, 4 figures, to be published in ICASSP2023