Related papers: Spherical Latent Motion Prior for Physics-Based Si…
Simulating the time evolution of physical systems is pivotal in many scientific and engineering problems. An open challenge in simulating such systems is their multi-resolution dynamics: a small fraction of the system is extremely dynamic,…
We present a Reinforcement Learning (RL)-based locomotion system for Cosmo, a custom-built humanoid robot designed for entertainment applications. Unlike traditional humanoids, entertainment robots present unique challenges due to…
Typical end-to-end formulations for learning robotic navigation involve predicting a small set of steering command actions (e.g., step forward, turn left, turn right, etc.) from images of the current state (e.g., a bird's-eye view of a SLAM…
Recent progress in human-robot collaboration makes fast and fluid interactions possible, even when human observations are partial and occluded. Methods like Interaction Probabilistic Movement Primitives (ProMP) model human trajectories…
Spring Loaded Inverted Pendulum (SLIP) model has a long history in describing running behavior in animals and humans as well as has been used as a design basis for robots capable of dynamic locomotion. Anchoring the SLIP for lossy physical…
Multi-agent motion prediction is challenging because it aims to foresee the future trajectories of multiple agents (\textit{e.g.} pedestrians) simultaneously in a complicated scene. Existing work addressed this challenge by either learning…
Humanoid control often leverages motion priors from human demonstrations to encourage natural behaviors. However, such demonstrations are frequently suboptimal or misaligned with robotic tasks due to embodiment differences, retargeting…
Dynamic manipulation is a key capability for advancing robot performance, enabling skills such as tossing. While recent learning-based approaches have pushed the field forward, most methods still rely on manually designed action…
We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches…
In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query. Considering that 3D human…
In this paper, we propose a novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.…
Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning…
To support humanoid robots in performing manipulation tasks, it is essential to study stable standing while accommodating upper-body motions. However, the limited controllable range of humanoid robots in a standing position affects the…
Humanoid robots hold great potential to perform various human-level skills, involving unified locomotion and manipulation in real-world settings. Driven by advances in machine learning and the strength of existing model-based approaches,…
Motion prediction is essential and challenging for autonomous vehicles and social robots. One challenge of motion prediction is to model the interaction among traffic actors, which could cooperate with each other to avoid collisions or form…
Semantic context is an important and useful cue for scene parsing in complicated natural images with a substantial amount of variations in objects and the environment. This paper proposes Spatially Constrained Location Prior (SCLP) for…
In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, our approach…
Non-prehensile (NP) manipulation, in which robots alter object states without forming stable grasps (for example, pushing, poking, or sliding), significantly broadens robotic manipulation capabilities when grasping is infeasible or…
Although humanoid and quadruped robots provide a wide range of capabilities, current control methods, such as Deep Reinforcement Learning, focus mainly on single skills. This approach is inefficient for solving more complicated tasks where…
Learning multiple gaits is non-trivial for legged robots, especially when encountering different terrains and velocity commands. In this work, we present an end-to-end training framework for learning multiple gaits for quadruped robots,…