Search

As humanoid robots transition from labs to real-world environments, it is essential to democratize robot control for non-expert users. Recent human-robot imitation algorithms focus on following a reference human motion with high precision, but they are susceptible to the quality of the reference motion and require the human operator to simplify its movements to match the robot's capabilities. Instead, we consider that the robot should understand and adapt the reference motion to its own abilities, facilitating the operator's task. For that, we introduce a deep-learning model that anticipates the robot's performance when imitating a given reference. Then, our system can generate multiple references given a high-level task command, assign a score to each of them, and select the best reference to achieve the desired robot behavior. Our Self-AWare model (SAW) ranks potential robot behaviors based on various criteria, such as fall likelihood, adherence to the reference motion, and smoothness. We integrate advanced motion generation, robot control, and SAW in one unique system, ensuring optimal robot behavior for any task command. For instance, SAW can anticipate falls with 99.29% accuracy. For more information check our project page: https://evm7.github.io/Self-AWare, Comment: Accepted to Humanoids 2024 and HFR 2024. Project Page: https://evm7.github.io/Self-AWare

Research continues to accumulate evidence that Goffin's cockatoos (Cacatua goffiniana) can solve wide sets of mechanical problems, such as tool use, tool manufacture, and solving mechanical puzzles. However, the proximate mechanisms underlying this adaptive behavior are largely unknown. In this study, we analyze how three Goffin's cockatoos learn to solve a specific mechanical puzzle, a lockbox. The observed behavior results from the interaction between a complex environment (the lockbox) and different processes that jointly govern the animals' behavior. We thus jointly analyze the parrots' (1) engagement, (2) sensorimotor skill learning, and (3) action selection. We find that neither of these aspects could solely explain the animals' behavioral adaptation and that a plausible model of proximate mechanisms (including adaptation) should thus also jointly address these aspects. We accompany this analysis with a discussion of methods that may be used to identify such mechanisms. A major point we want to make is, that it is implausible to reliably identify a detailed model from the limited data of one or a few studies. Instead, we advocate for a more coarse approach that first establishes constraints on proximate mechanisms before specific, detailed models are formulated. We exercise this idea on the data we present in this study., Comment: Accepted for publication at journal Adaptive Behavior with SAGE publishing

This paper addresses the critical need for refining robot motions that, despite achieving a high visual similarity through human-to-humanoid retargeting methods, fall short of practical execution in the physical realm. Existing techniques in the graphics community often prioritize visual fidelity over physics-based feasibility, posing a significant challenge for deploying bipedal systems in practical applications. Our research introduces a constrained reinforcement learning algorithm to produce physics-based high-quality motion imitation onto legged humanoid robots that enhance motion resemblance while successfully following the reference human trajectory. We name our framework: I-CTRL. By reformulating the motion imitation problem as a constrained refinement over non-physics-based retargeted motions, our framework excels in motion imitation with simple and unique rewards that generalize across four robots. Moreover, our framework can follow large-scale motion datasets with a unique RL agent. The proposed approach signifies a crucial step forward in advancing the control of bipedal robots, emphasizing the importance of aligning visual and physical realism for successful motion imitation.

COVID-19 appeared abruptly in early 2020, requiring a rapid response amid a context of great uncertainty. Good quality data and knowledge was initially lacking, and many early models had to be developed with causal assumptions and estimations built in to supplement limited data, often with no reliable approach for identifying, validating and documenting these causal assumptions. Our team embarked on a knowledge engineering process to develop a causal knowledge base consisting of several causal BNs for diverse aspects of COVID-19. The unique challenges of the setting lead to experiments with the elicitation approach, and what emerged was a knowledge engineering method we call Causal Knowledge Engineering (CKE). The CKE provides a structured approach for building a causal knowledge base that can support the development of a variety of application-specific models. Here we describe the CKE method, and use our COVID-19 work as a case study to provide a detailed discussion and analysis of the method., Comment: 22 pages (plus 19 pages in appendices), 9 figures, submitted for review

The typical phases of Bayesian network (BN) structured development include specification of purpose and scope, structure development, parameterisation and validation. Structure development is typically focused on qualitative issues and parameterisation quantitative issues, however there are qualitative and quantitative issues that arise in both phases. A common step that occurs after the initial structure has been developed is to perform a rough parameterisation that only captures and illustrates the intended qualitative behaviour of the model. This is done prior to a more rigorous parameterisation, ensuring that the structure is fit for purpose, as well as supporting later development and validation. In our collective experience and in discussions with other modellers, this step is an important part of the development process, but is under-reported in the literature. Since the practice focuses on qualitative issues, despite being quantitative in nature, we call this step qualitative parameterisation and provide an outline of its role in the BN development process., Comment: 6 pages, 2 figures, technical note

Integrating robots into populated environments is a complex challenge that requires an understanding of human social dynamics. In this work, we propose to model social motion forecasting in a shared human-robot representation space, which facilitates us to synthesize robot motions that interact with humans in social scenarios despite not observing any robot in the motion training. We develop a transformer-based architecture called ECHO, which operates in the aforementioned shared space to predict the future motions of the agents encountered in social scenarios. Contrary to prior works, we reformulate the social motion problem as the refinement of the predicted individual motions based on the surrounding agents, which facilitates the training while allowing for single-motion forecasting when only one human is in the scene. We evaluate our model in multi-person and human-robot motion forecasting tasks and obtain state-of-the-art performance by a large margin while being efficient and performing in real-time. Additionally, our qualitative results showcase the effectiveness of our approach in generating human-robot interaction behaviors that can be controlled via text commands. Webpage: https://evm7.github.io/ECHO/, Comment: Accepted at ICRA 2024. Webpage: https://evm7.github.io/ECHO/

In this paper, we present a novel formulation to model the effects of a locked differential on the lateral dynamics of an autonomous open-wheel racecar. The model is used in a Model Predictive Controller in which we included a micro-steps discretization approach to accurately linearize the dynamics and produce a prediction suitable for real-time implementation. The stability analysis of the model is presented, as well as a brief description of the overall planning and control scheme which includes an offline trajectory generation pipeline, an online local speed profile planner, and a low-level longitudinal controller. An improvement of the lateral path tracking is demonstrated in preliminary experimental results that have been produced on a Dallara AV-21 during the first Indy Autonomous Challenge event on the Monza F1 racetrack. Final adjustments and tuning have been performed in a high-fidelity simulator demonstrating the effectiveness of the solution when performing close to the tire limits., Comment: Presented at the 2023 IEEE 11th International Conference on Systems and Control, Sousse, Tunisia, December 18-20, 2023

We consider the problem of learning causal Directed Acyclic Graphs (DAGs) using combinations of observational and interventional experimental data. Current methods tailored to this setting assume that interventions either destroy parent-child relations of the intervened (target) nodes or only alter such relations without modifying the parent sets, even when the intervention targets are unknown. We relax this assumption by proposing a Bayesian method for causal discovery from general interventions, which allow for modifications of the parent sets of the unknown targets. Even in this framework, DAGs and general interventions may be identifiable only up to some equivalence classes. We provide graphical characterizations of such interventional Markov equivalence and devise compatible priors for Bayesian inference that guarantee score equivalence of indistinguishable structures. We then develop a Markov Chain Monte Carlo (MCMC) scheme to approximate the posterior distribution over DAGs, intervention targets and induced parent sets. Finally, we evaluate the proposed methodology on both simulated and real protein expression data.

Robots are becoming increasingly integrated into our lives, assisting us in various tasks. To ensure effective collaboration between humans and robots, it is essential that they understand our intentions and anticipate our actions. In this paper, we propose a Human-Object Interaction (HOI) anticipation framework for collaborative robots. We propose an efficient and robust transformer-based model to detect and anticipate HOIs from videos. This enhanced anticipation empowers robots to proactively assist humans, resulting in more efficient and intuitive collaborations. Our model outperforms state-of-the-art results in HOI detection and anticipation in VidHOI dataset with an increase of 1.76% and 1.04% in mAP respectively while being 15.4 times faster. We showcase the effectiveness of our approach through experimental results in a real robot, demonstrating that the robot's ability to anticipate HOIs is key for better Human-Robot Interaction. More information can be found on our project webpage: https://evm7.github.io/HOI4ABOT_page/, Comment: Proceedings in Conference on Robot Learning 2023. Webpage: https://evm7.github.io/HOI4ABOT_page/

This paper introduces a novel deep-learning approach for human-to-robot motion retargeting, enabling robots to mimic human poses accurately. Contrary to prior deep-learning-based works, our method does not require paired human-to-robot data, which facilitates its translation to new robots. First, we construct a shared latent space between humans and robots via adaptive contrastive learning that takes advantage of a proposed cross-domain similarity metric between the human and robot poses. Additionally, we propose a consistency term to build a common latent space that captures the similarity of the poses with precision while allowing direct robot motion control from the latent space. For instance, we can generate in-between motion through simple linear interpolation between two projected human poses. We conduct a comprehensive evaluation of robot control from diverse modalities (i.e., texts, RGB videos, and key poses), which facilitates robot control for non-expert users. Our model outperforms existing works regarding human-to-robot retargeting in terms of efficiency and precision. Finally, we implemented our method in a real robot with self-collision avoidance through a whole-body controller to showcase the effectiveness of our approach. More information on our website https://evm7.github.io/UnsH2R/, Comment: Accepted to Humanoids 2023. Website: https://evm7.github.io/UnsH2R/

Cloud computing offers an opportunity to run compute-resource intensive climate models at scale by parallelising model runs such that datasets useful to the exoplanet community can be produced efficiently. To better understand the statistical distributions and properties of potentially habitable planetary atmospheres we implemented a parallelised climate modelling tool to scan a range of hypothetical atmospheres.Starting with a modern day Earth atmosphere, we iteratively and incrementally simulated a range of atmospheres to infer the landscape of the multi-parameter space, such as the abundances of biological mediated gases (\ce{O2}, \ce{CO2}, \ce{H2O}, \ce{CH4}, \ce{H2}, and \ce{N2}) that would yield `steady state' planetary atmospheres on Earth-like planets around solar-type stars. Our current datasets comprises of \numatmospheres simulated models of exoplanet atmospheres and is available publicly on the NASA Exoplanet Archive. Our scalable approach of analysing atmospheres could also help interpret future observations of planetary atmospheres by providing estimates of atmospheric gas fluxes and temperatures as a function of altitude. Such data could enable high-throughput first-order assessment of the potential habitability of exoplanetary surfaces and sepcan be a learning dataset for machine learning applications in the atmospheric and exoplanet science domain., Comment: 9 pages, 6 figures

The synthesis of human motion has traditionally been addressed through task-dependent models that focus on specific challenges, such as predicting future motions or filling in intermediate poses conditioned on known key-poses. In this paper, we present a novel task-independent model called UNIMASK-M, which can effectively address these challenges using a unified architecture. Our model obtains comparable or better performance than the state-of-the-art in each field. Inspired by Vision Transformers (ViTs), our UNIMASK-M model decomposes a human pose into body parts to leverage the spatio-temporal relationships existing in human motion. Moreover, we reformulate various pose-conditioned motion synthesis tasks as a reconstruction problem with different masking patterns given as input. By explicitly informing our model about the masked joints, our UNIMASK-M becomes more robust to occlusions. Experimental results show that our model successfully forecasts human motion on the Human3.6M dataset. Moreover, it achieves state-of-the-art results in motion inbetweening on the LaFAN1 dataset, particularly in long transition periods. More information can be found on the project website https://evm7.github.io/UNIMASKM-page/, Comment: Accepted to AAAI2024. Webpage: https://evm7.github.io/UNIMASKM-page/

Understanding the human-object interactions (HOIs) from a video is essential to fully comprehend a visual scene. This line of research has been addressed by detecting HOIs from images and lately from videos. However, the video-based HOI anticipation task in the third-person view remains understudied. In this paper, we design a framework to detect current HOIs and anticipate future HOIs in videos. We propose to leverage human gaze information since people often fixate on an object before interacting with it. These gaze features together with the scene contexts and the visual appearances of human-object pairs are fused through a spatio-temporal transformer. To evaluate the model in the HOI anticipation task in a multi-person scenario, we propose a set of person-wise multi-label metrics. Our model is trained and validated on the VidHOI dataset, which contains videos capturing daily life and is currently the largest video HOI dataset. Experimental results in the HOI detection task show that our approach improves the baseline by a great margin of 36.3% relatively. Moreover, we conduct an extensive ablation study to demonstrate the effectiveness of our modifications and extensions to the spatio-temporal transformer. Our code is publicly available on https://github.com/nizhf/hoi-prediction-gaze-transformer., Comment: Accepted by CVIU https://doi.org/10.1016/j.cviu.2023.103741

After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days. In this paper, our objective is to evaluate the potential of diffusion probabilistic models for 3D human motion-related tasks. To this end, this paper presents a study of employing diffusion probabilistic models to predict future 3D human motion(s) from the previously observed motion. Based on the Human 3.6M and HumanEva-I datasets, our results show that diffusion probabilistic models are competitive for both single (deterministic) and multiple (stochastic) 3D motion prediction tasks, after finishing a single training process. In addition, we find out that diffusion probabilistic models can offer an attractive compromise, since they can strike the right balance between the likelihood and diversity of the predicted future motions. Our code is publicly available on the project website: https://sites.google.com/view/diffusion-motion-prediction., Comment: 7 pages, 3 figures, ICRA 2023

Comprehending human motion is a fundamental challenge for developing Human-Robot Collaborative applications. Computer vision researchers have addressed this field by only focusing on reducing error in predictions, but not taking into account the requirements to facilitate its implementation in robots. In this paper, we propose a new model based on Transformer that simultaneously deals with the real time 3D human motion forecasting in the short and long term. Our 2-Channel Transformer (2CH-TR) is able to efficiently exploit the spatio-temporal information of a shortly observed sequence (400ms) and generates a competitive accuracy against the current state-of-the-art. 2CH-TR stands out for the efficient performance of the Transformer, being lighter and faster than its competitors. In addition, our model is tested in conditions where the human motion is severely occluded, demonstrating its robustness in reconstructing and predicting 3D human motion in a highly noisy environment. Our experiment results show that the proposed 2CH-TR outperforms the ST-Transformer, which is another state-of-the-art model based on the Transformer, in terms of reconstruction and prediction under the same conditions of input prefix. Our model reduces in 8.89% the mean squared error of ST-Transformer in short-term prediction, and 2.57% in long-term prediction in Human3.6M dataset with 400ms input prefix. Webpage: https://evm7.github.io/2CHTR-page/, Comment: Accepted to IROS2022. Webpage: https://evm7.github.io/2CHTR-page/

Neuroscience is moving towards a more integrative discipline, where understanding brain function requires consolidating the accumulated evidence seen across experiments, species, and measurement techniques. A remaining challenge on that path is integrating such heterogeneous data into analysis workflows such that consistent and comparable conclusions can be distilled as an experimental basis for models and theories. Here, we propose a solution in the context of slow wave activity ($<1$ Hz), which occurs during unconscious brain states like sleep and general anesthesia, and is observed across diverse experimental approaches. We address the issue of integrating and comparing heterogeneous data by conceptualizing a general pipeline design that is adaptable to a variety of inputs and applications. Furthermore, we present the Collaborative Brain Wave Analysis Pipeline (Cobrawap) as a concrete, reusable software implementation to perform broad, detailed, and rigorous comparisons of slow wave characteristics across multiple, openly available ECoG and calcium imaging datasets.

To anticipate how a human would act in the future, it is essential to understand the human intention since it guides the human towards a certain goal. In this paper, we propose a hierarchical architecture which assumes a sequence of human action (low-level) can be driven from the human intention (high-level). Based on this, we deal with Long-Term Action Anticipation task in egocentric videos. Our framework first extracts two level of human information over the N observed videos human actions through a Hierarchical Multi-task MLP Mixer (H3M). Then, we condition the uncertainty of the future through an Intention-Conditioned Variational Auto-Encoder (I-CVAE) that generates K stable predictions of the next Z=20 actions that the observed human might perform. By leveraging human intention as high-level information, we claim that our model is able to anticipate more time-consistent actions in the long-term, thus improving the results over baseline methods in EGO4D Challenge. This work ranked first in both CVPR@2022 and ECVV@2022 EGO4D LTA Challenge by providing more plausible anticipated sequences, improving the anticipation of nouns and overall actions. Webpage: https://evm7.github.io/icvae-page/, Comment: Winner of CVPR@2022 and ECCV@2022 EGO4D LTA Challenge. Accepted in WACV2023. Webpage: https://evm7.github.io/icvae-page/

Background: In neurophysiological data, latency refers to a global shift of spikes from one spike train to the next, either caused by response onset fluctuations or by finite propagation speed. Such systematic shifts in spike timing lead to a spurious decrease in synchrony which needs to be corrected. New Method: We propose a new algorithm of multivariate latency correction suitable for sparse data for which the relevant information is not primarily in the rate but in the timing of each individual spike. The algorithm is designed to correct systematic delays while maintaining all other kinds of noisy disturbances. It consists of two steps, spike matching and distance minimization between the matched spikes using simulated annealing. Results: We show its effectiveness on simulated and real data: cortical propagation patterns recorded via calcium imaging from mice before and after stroke. Using simulations of these data we also establish criteria that can be evaluated beforehand in order to anticipate whether our algorithm is likely to yield a considerable improvement for a given dataset. Comparison with Existing Method(s): Existing methods of latency correction rely on adjusting peaks in rate profiles, an approach that is not feasible for spike trains with low firing in which the timing of individual spikes contains essential information. Conclusions: For any given dataset the criterion for applicability of the algorithm can be evaluated quickly and in case of a positive outcome the latency correction can be applied easily since the source codes of the algorithm are publicly available., Comment: 15 pages, 9 figures

Directed Acyclic Graphs (DAGs) provide a powerful framework to model causal relationships among variables in multivariate settings; in addition, through the do-calculus theory, they allow for the identification and estimation of causal effects between variables also from pure observational data. In this setting, the process of inferring the DAG structure from the data is referred to as causal structure learning or causal discovery. We introduce BCDAG, an R package for Bayesian causal discovery and causal effect estimation from Gaussian observational data, implementing the Markov chain Monte Carlo (MCMC) scheme proposed by Castelletti & Mascaro (2021). Our implementation scales efficiently with the number of observations and, whenever the DAGs are sufficiently sparse, with the number of variables in the dataset. The package also provides functions for convergence diagnostics and for visualizing and summarizing posterior inference. In this paper, we present the key features of the underlying methodology along with its implementation in BCDAG. We then illustrate the main functions and algorithms on both real and simulated datasets.

This paper has introduced a novel approach for the real-time estimation of 3D tactile forces exerted by human fingertips via vision only. The introduced approach is entirely monocular vision-based and does not require any physical force sensor. Therefore, it is scalable, non-intrusive, and easily fused with other perception systems such as body pose estimation, making it ideal for HRI applications where force sensing is necessary. The introduced approach consists of three main modules: finger tracking for detection and tracking of each individual finger, image alignment for preserving the spatial information in the images, and the force model for estimating the 3D forces from coloration patterns in the images. The model has been implemented experimentally, and the results have shown a maximum RMS error of 8.4% (for the entire range of force levels) along all three directions. The estimation accuracy is comparable to the offline models in the literature, such as EigneNail, while, this model is capable of performing force estimation at 30 frames per second., Comment: pending co-authors permission to publish