Search

The process of satisfying daily demands is a fundamental aspect of humans' daily lives. With the advancement of embodied AI, robots are increasingly capable of satisfying human demands. Demand-driven navigation (DDN) is a task in which an agent must locate an object to satisfy a specified demand instruction, such as ``I am thirsty.'' The previous study typically assumes that each demand instruction requires only one object to be fulfilled and does not consider individual preferences. However, the realistic human demand may involve multiple objects. In this paper, we introduce the Multi-object Demand-driven Navigation (MO-DDN) benchmark, which addresses these nuanced aspects, including multi-object search and personal preferences, thus making the MO-DDN task more reflective of real-life scenarios compared to DDN. Building upon previous work, we employ the concept of ``attribute'' to tackle this new task. However, instead of solely relying on attribute features in an end-to-end manner like DDN, we propose a modular method that involves constructing a coarse-to-fine attribute-based exploration agent (C2FAgent). Our experimental results illustrate that this coarse-to-fine exploration strategy capitalizes on the advantages of attributes at various decision-making levels, resulting in superior performance compared to baseline methods. Code and video can be found at https://sites.google.com/view/moddn., Comment: Accepted at NeurIPS 2024; 39 pages, 11 figures

This paper improves upon existing data pruning methods for image classification by introducing a novel pruning metric and pruning procedure based on importance sampling. The proposed pruning metric explicitly accounts for data separability, data integrity, and model uncertainty, while the sampling procedure is adaptive to the pruning ratio and considers both intra-class and inter-class separation to further enhance the effectiveness of pruning. Furthermore, the sampling method can readily be applied to other pruning metrics to improve their performance. Overall, the proposed approach scales well to high pruning ratio and generalizes better across different classification models, as demonstrated by experiments on four benchmark datasets, including the fine-grained classification scenario.

Enabling robots to navigate following diverse language instructions in unexplored environments is an attractive goal for human-robot interaction. However, this goal is challenging because different navigation tasks require different strategies. The scarcity of instruction navigation data hinders training an instruction navigation model with varied strategies. Therefore, previous methods are all constrained to one specific type of navigation instruction. In this work, we propose InstructNav, a generic instruction navigation system. InstructNav makes the first endeavor to handle various instruction navigation tasks without any navigation training or pre-built maps. To reach this goal, we introduce Dynamic Chain-of-Navigation (DCoN) to unify the planning process for different types of navigation instructions. Furthermore, we propose Multi-sourced Value Maps to model key elements in instruction navigation so that linguistic DCoN planning can be converted into robot actionable trajectories. With InstructNav, we complete the R2R-CE task in a zero-shot way for the first time and outperform many task-training methods. Besides, InstructNav also surpasses the previous SOTA method by 10.48% on the zero-shot Habitat ObjNav and by 86.34% on demand-driven navigation DDN. Real robot experiments on diverse indoor scenes further demonstrate our method's robustness in coping with the environment and instruction variations., Comment: Submitted to CoRL 2024

Fluxonium qubits are recognized for their high coherence times and high operation fidelities, attributed to their unique design incorporating over 100 Josephson junctions per superconducting loop. However, this complexity poses significant fabrication challenges, particularly in achieving high yield and junction uniformity with traditional methods. Here, we introduce an overlap process for Josephson junction fabrication that achieves nearly 100% yield and maintains uniformity across a 2-inch wafer with less than 5% variation for the phase slip junction and less than 2% for the junction array. Our compact junction array design facilitates fluxonium qubits with energy relaxation times exceeding 1 millisecond at the flux frustration point, demonstrating consistency with state-of-the-art dielectric loss tangents and flux noise across multiple devices. This work suggests the scalability of high coherence fluxonium processors using CMOS-compatible processes, marking a significant step towards practical quantum computing.

In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model needs to retrieve a real image of it from an online store's catalog. A standard approach for such a problem is learning a feature space of images where Euclidean distances reflect similarity. Even without human annotations, which may be expensive to acquire, prior methods function reasonably well using unlabeled images for training. Our problem constraint takes this further to scenarios where the two domains do not necessarily share any common categories in training data. This can occur when the two domains in question come from different versions of some biometric sensor recording identities of different people. We posit a simple solution, which is to generate synthetic data to fill in these missing category examples across domains. This, we do via category preserving translation of images from one visual domain to another. We compare approaches specifically trained for this translation for a pair of domains, as well as those that can use large-scale pre-trained text-to-image diffusion models via prompts, and find that the latter can generate better replacement synthetic data, leading to more accurate cross-domain retrieval models. Our best SynCDR model can outperform prior art by up to 15\%. Code for our work is available at https://github.com/samarth4149/SynCDR ., Comment: Pre-print

The task of Visual Object Navigation (VON) involves an agent's ability to locate a particular object within a given scene. In order to successfully accomplish the VON task, two essential conditions must be fulfilled:1) the user must know the name of the desired object; and 2) the user-specified object must actually be present within the scene. To meet these conditions, a simulator can incorporate pre-defined object names and positions into the metadata of the scene. However, in real-world scenarios, it is often challenging to ensure that these conditions are always met. Human in an unfamiliar environment may not know which objects are present in the scene, or they may mistakenly specify an object that is not actually present. Nevertheless, despite these challenges, human may still have a demand for an object, which could potentially be fulfilled by other objects present within the scene in an equivalent manner. Hence, we propose Demand-driven Navigation (DDN), which leverages the user's demand as the task instruction and prompts the agent to find the object matches the specified demand. DDN aims to relax the stringent conditions of VON by focusing on fulfilling the user's demand rather than relying solely on predefined object categories or names. We propose a method first acquire textual attribute features of objects by extracting common knowledge from a large language model. These textual attribute features are subsequently aligned with visual attribute features using Contrastive Language-Image Pre-training (CLIP). By incorporating the visual attribute features as prior knowledge, we enhance the navigation process. Experiments on AI2Thor with the ProcThor dataset demonstrate the visual attribute features improve the agent's navigation performance and outperform the baseline methods commonly used in VON., Comment: NeurIPS 2023; Project page:https://sites.google.com/view/demand-driven-navigation; Code: https://github.com/whcpumpkin/Demand-driven-navigation

The fluxonium qubits have emerged as a promising platform for gate-based quantum information processing. However, their extraordinary protection against charge fluctuations comes at a cost: when coupled capacitively, the qubit-qubit interactions are restricted to XX-interactions. Consequently, effective XX- or XZ-interactions are only constructed either by temporarily populating higher-energy states, or by exploiting perturbative effects under microwave driving. Instead, we propose and demonstrate an inductive coupling scheme, which offers a wide selection of native qubit-qubit interactions for fluxonium. In particular, we leverage a built-in, flux-controlled ZZ-interaction to perform qubit entanglement. To combat the increased flux-noise-induced dephasing away from the flux-insensitive position, we use a continuous version of the dynamical decoupling scheme to perform noise filtering. Combining these, we demonstrate a 20 ns controlled-Z (CZ) gate with a mean fidelity of 99.53%. More than confirming the efficacy of our gate scheme, this high-fidelity result also reveals a promising but rarely explored parameter space uniquely suitable for gate operations between fluxonium qubits.

Despite recent advances in video-based action recognition and robust spatio-temporal modeling, most of the proposed approaches rely on the abundance of computational resources to afford running huge and computation-intensive convolutional or transformer-based neural networks to obtain satisfactory results. This limits the deployment of such models on edge devices with limited power and computing resources. In this work we investigate an important smart home application, video based delivery detection, and present a simple and lightweight pipeline for this task that can run on resource-constrained doorbell cameras. Our method relies on motion cues to generate a set of coarse activity proposals followed by their classification with a mobile-friendly 3DCNN network. To train we design a novel semi-supervised attention module that helps the network to learn robust spatio-temporal features and adopt an evidence-based optimization objective that allows for quantifying the uncertainty of predictions made by the network. Experimental results on our curated delivery dataset shows the significant effectiveness of our pipeline and highlights the benefits of our training phase novelties to achieve free and considerable inference-time performance gains., Comment: Accepted to the 2024 WACV conference

Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories.

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides better initialization for other skills, improving the sample efficiency for skill learning. In skill planning, we leverage the prior knowledge in Large Language Models to find the relationships between skills and build a skill graph. When the agent is solving a task, our skill search algorithm walks on the skill graph and generates the proper skill plans for the agent. In experiments, our method accomplishes 40 diverse Minecraft tasks, where many tasks require sequentially executing for more than 10 skills. Our method outperforms baselines by a large margin and is the most sample-efficient demonstration-free RL method to solve Minecraft Tech Tree tasks. The project's website and code can be found at https://sites.google.com/view/plan4mc., Comment: 24 pages, presented in Foundation Models for Decision Making Workshop at NeurIPS 2023

In dense neighborhoods, there are often dozens of homes in close proximity. This can either be a tight city-block with many single-family homes (SFHs), or a multiple dwelling units (MDU) complex (such as a big apartment building or condominium). Each home in such a neighborhood (either a SFH or a single unit in a MDU complex) has its own Wi-Fi access point (AP). Because there are few (typically 2 or 3) non-overlapping radio channels for Wi-Fi, neighboring homes may find themselves sharing a channel and competing over airtime, which may cause bad experience of slow internet (long latency, buffering while streaming movies, etc.). Wi-Fi optimization over all the APs in a dense neighborhood is highly desired to provide the best user experience. We present a method for Wi-Fi channel selection in a centralized way for all the APs in a dense neighborhood. We describe how to use recent observations to estimate the potential-pain matrix - for each pair of APs, how much Wi-Fi-pain would they cause each other if they were on the same channel. We formulate an optimization problem - finding a channel allocation (which channel each home should use) that minimizes the total Wi-Fi-pain in the neighborhood. We design an optimization algorithm that uses gradient descent over a neural network to solve the optimization problem. We describe initial results from offline experiments comparing our optimization solver to an off-the-shelf mixed-integer-programming solver. In our experiments we show that the off-the-shelf solver manages to find a better (lower total pain) solution on the train data (from the recent days), but our neural-network solver generalizes better - it finds a solution that achieves lower total pain for the test data (tomorrow)., Comment: We discussed this work in the 2022 Fall Technical Forum as part of SCTE Cable-Tec Expo. This paper was published in SCTE Technical Journal. For citing this work, please cite the original publication

Imagine a map of your home with all of your connected devices (computers, TVs, voice control devices, printers, security cameras, etc.), in their location. You could then easily group devices into user-profiles, monitor Wi-Fi quality and activity in different areas of your home, and even locate a lost tablet in your home. MapiFi is a method to generate that map of the devices in a home. The first part of MapiFi involves the user (either a technician or the resident) walking around the home with a mobile device that listens to Wi-Fi radio channels. The mobile device detects Wi-Fi packets that come from all of the home's devices that connect to the gateway and measures their signal strengths (ignoring the content of the packets). The second part is an algorithm that uses all the signal-strength measurements to estimate the locations of all the devices in the home. Then, MapiFi visualizes the home's space as a coordinate system with devices marked as points in this space. A patent has been filed based on this technology. This paper was published in SCTE Technical Journal (see published paper at https://wagtail-prod-storage.s3.amazonaws.com/documents/SCTE_Technical_Journal_V1N3.pdf)., Comment: 6 pages, 4 figures, published in SCTE Technical Journal, patent pending at US Patent and Trademark Office

While using a speaker verification (SV) based system in a commercial application, it is important that customers have an inclusive experience irrespective of their gender, age, or ethnicity. In this paper, we analyze the impact of gender and age on SV and find that for a desired common False Acceptance Rate (FAR) across different gender and age groups, the False Rejection Rate (FRR) is different for different gender and age groups. To optimize FRR for all users for a desired FAR, we propose a context (e.g. gender, age) adaptive thresholding framework for SV. The context can be available as prior information for many practical applications. We also propose a concatenated gender/age detection model to algorithmically derive the context in absence of such prior information. We experimentally show that our context-adaptive thresholding method is effective in building a more efficient inclusive SV system. Specifically, we show that we can reduce FRR for specific gender for a desired FAR on the voxceleb1 test set by using gender-specific thresholds. Similar analysis on OGI kids' speech corpus shows that by using an age-specific threshold, we can significantly reduce FRR for certain age groups for desired FAR.

Wastewater treatment plants are designed to eliminate pollutants and alleviate environmental pollution. However, the construction and operation of WWTPs consume resources, emit greenhouse gases (GHGs) and produce residual sludge, thus require further optimization. WWTPs are complex to control and optimize because of high nonlinearity and variation. This study used a novel technique, multi-agent deep reinforcement learning, to simultaneously optimize dissolved oxygen and chemical dosage in a WWTP. The reward function was specially designed from life cycle perspective to achieve sustainable optimization. Five scenarios were considered: baseline, three different effluent quality and cost-oriented scenarios. The result shows that optimization based on LCA has lower environmental impacts compared to baseline scenario, as cost, energy consumption and greenhouse gas emissions reduce to 0.890 CNY/m3-ww, 0.530 kWh/m3-ww, 2.491 kg CO2-eq/m3-ww respectively. The cost-oriented control strategy exhibits comparable overall performance to the LCA driven strategy since it sacrifices environmental bene ts but has lower cost as 0.873 CNY/m3-ww. It is worth mentioning that the retrofitting of WWTPs based on resources should be implemented with the consideration of impact transfer. Specifically, LCA SW scenario decreases 10 kg PO4-eq in eutrophication potential compared to the baseline within 10 days, while significantly increases other indicators. The major contributors of each indicator are identified for future study and improvement. Last, the author discussed that novel dynamic control strategies required advanced sensors or a large amount of data, so the selection of control strategies should also consider economic and ecological conditions.

The expanding population and rapid urbanisation, in particular in the Global South, are leading to global challenges on resource supply stress and rising waste generation. A transformation to resource-circular systems and sustainable recovery of carbon-containing and nutrient-rich waste offers a way to tackle such challenges. Eco-industrial parks have the potential to capture symbioses across individual waste producers, leading to more effective waste-recovery schemes. With whole-system design, economically attractive approaches can be achieved, reducing the nvironmental impacts while increasing the recovery of high-value resources. In this paper, an optimisation framework is developed to enable such design, allowing for wide ranging treatment options to be considered capturing both technological and fnancial detail. As well as technology selection, the framework also accounts for spatial aspects, with the design of suitable transport networks playing a key role. A range of scenarios are investigated using the network, highlighting the multi-faceted nature of the problem. The need to incorporate the impact of resource recovery at the design stage is shown to be of particular importance., Comment: 31 pages, 13 figures

Classification is a pivotal function for many computer vision tasks such as object classification, detection, scene segmentation. Multinomial logistic regression with a single final layer of dense connections has become the ubiquitous technique for CNN-based classification. While these classifiers project a mapping between the input and a set of output category classes, they do not typically yield a comprehensive description of the category. In particular, when a CNN based image classifier correctly identifies the image of a Chimpanzee, its output does not clarify that Chimpanzee is a member of Primate, Mammal, Chordate families and a living thing. We propose a multilayer dense connectivity for concurrent prediction of category and its conceptual superclasses in hierarchical order by the same CNN. We experimentally demonstrate that our proposed network can simultaneously predict both the coarse superclasses and finer categories better than several existing algorithms in multiple datasets.

We propose a semi-supervised learning approach for video classification, VideoSSL, using convolutional neural networks (CNN). Like other computer vision tasks, existing supervised video classification methods demand a large amount of labeled data to attain good performance. However, annotation of a large dataset is expensive and time consuming. To minimize the dependence on a large annotated dataset, our proposed semi-supervised method trains from a small number of labeled examples and exploits two regulatory signals from unlabeled data. The first signal is the pseudo-labels of unlabeled examples computed from the confidences of the CNN being trained. The other is the normalized probabilities, as predicted by an image classifier CNN, that captures the information about appearances of the interesting objects in the video. We show that, under the supervision of these guiding signals from unlabeled examples, a video classification CNN can achieve impressive performances utilizing a small fraction of annotated examples on three publicly available datasets: UCF101, HMDB51 and Kinetics.

This paper proposes a novel approach for crowd counting in low to high density scenarios in static images. Current approaches cannot handle huge crowd diversity well and thus perform poorly in extreme cases, where the crowd density in different regions of an image is either too low or too high, leading to crowd underestimation or overestimation. The proposed solution is based on the observation that detecting and handling such extreme cases in a specialized way leads to better crowd estimation. Additionally, existing methods find it hard to differentiate between the actual crowd and the cluttered background regions, resulting in further count overestimation. To address these issues, we propose a simple yet effective modular approach, where an input image is first subdivided into fixed-size patches and then fed to a four-way classification module labeling each image patch as low, medium, high-dense or no-crowd. This module also provides a count for each label, which is then analyzed via a specifically devised novel decision module to decide whether the image belongs to any of the two extreme cases (very low or very high density) or a normal case. Images, specified as high- or low-density extreme or a normal case, pass through dedicated zooming or normal patch-making blocks respectively before routing to the regressor in the form of fixed-size patches for crowd estimate. Extensive experimental evaluations demonstrate that the proposed approach outperforms the state-of-the-art methods on four benchmarks under most of the evaluation criteria.

We address the recognition of agent-in-place actions, which are associated with agents who perform them and places where they occur, in the context of outdoor home surveillance. We introduce a representation of the geometry and topology of scene layouts so that a network can generalize from the layouts observed in the training set to unseen layouts in the test set. This Layout-Induced Video Representation (LIVR) abstracts away low-level appearance variance and encodes geometric and topological relationships of places in a specific scene layout. LIVR partitions the semantic features of a video clip into different places to force the network to learn place-based feature descriptions; to predict the confidence of each action, LIVR aggregates features from the place associated with an action and its adjacent places on the scene layout. We introduce the Agent-in-Place Action dataset to show that our method allows neural network models to generalize significantly better to unseen scenes.

This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting moving objects with background subtraction running on the camera, and filtering out nuisance motion events (e.g., trees, cloud, shadow, rain/snow, flag) with deep learning based object detection and tracking running on cloud. The method is extremely slow and therefore not cost effective, and does not fully leverage the spatial-temporal redundancies with a pre-trained off-the-shelf object detector. To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video. ReMotENet parses an entire video clip in one forward pass of a neural network to achieve significant speedup. Meanwhile, it exploits the properties of home surveillance videos, e.g., relevant motion is sparse both spatially and temporally, and enhances 3D ConvNets with a spatial-temporal attention model and reference-frame subtraction to encourage the network to focus on the relevant moving objects. Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k times) on GPU devices. Our network is efficient, compact and light-weight. It can detect relevant motion on a 15s surveillance video clip within 4-8 milliseconds on a GPU and a fraction of second (0.17-0.39) on a CPU with a model size of less than 1MB., Comment: WACV18