Related papers: Retargeting Matters: General Motion Retargeting fo…
Text-driven human motion generation, as one of the vital tasks in computer-aided content creation, has recently attracted increasing attention. While pioneering research has largely focused on improving numerical performance metrics on…
Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to…
Robots are good at performing repetitive tasks in modern manufacturing industries. However, robot motions are mostly planned and preprogrammed with a notable lack of adaptivity to task changes. Even for slightly changed tasks, the whole…
We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used…
Humanoid robots exhibit significant potential in executing diverse human-level skills. However, current research predominantly relies on data-driven approaches that necessitate extensive training datasets to achieve robust multimodal…
Recovering world-coordinate human motion from monocular videos with humanoid robot retargeting is significant for embodied intelligence and robotics. To avoid complex SLAM pipelines or heavy temporal models, we propose a lightweight,…
There are several challenges in developing a model for multi-tasking humanoid control. Reinforcement learning and imitation learning approaches are quite popular in this domain. However, there is a trade-off between the two. Reinforcement…
We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high dimensionality of humanoids and the inherent difficulties in reinforcement learning,…
Developing robust autonomous loco-manipulation skills for humanoids remains an open problem in robotics. While RL has been applied successfully to legged locomotion, applying it to complex, interaction-rich manipulation tasks is harder…
Robust disturbance rejection remains a longstanding challenge in humanoid locomotion, particularly on unstructured terrains where sensing is unreliable and model mismatch is pronounced. While perception information, such as height map,…
We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…
Human pose, action, and motion generation are critical for applications in digital humans, character animation, and humanoid robotics. However, many existing methods struggle to produce physically plausible movements that are consistent…
Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), struggle to cultivate generalizability across diverse…
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…
The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward…
Humanoid locomotion requires not only accurate command tracking for navigation but also compliant responses to external forces during human interaction. Despite significant progress, existing RL approaches mainly emphasize robustness,…
Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain. In particular, while low-level motion tracking and trajectory-following…
This paper focuses on a critical challenge in robotics: translating text-driven human motions into executable actions for humanoid robots, enabling efficient and cost-effective learning of new behaviors. While existing text-to-motion…
We present a unified gait-conditioned reinforcement learning framework that enables humanoid robots to perform standing, walking, running, and smooth transitions within a single recurrent policy. A compact reward routing mechanism…
When a gait of a bipedal robot is developed using deep reinforcement learning, reference trajectories may or may not be used. Each approach has its advantages and disadvantages, and the choice of method is up to the control developer. This…