Related papers: Learning Task-Invariant Properties via Dreamer: En…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Dynamic jumping on high platforms and over gaps differentiates legged robots from wheeled counterparts. Dynamic locomotion on abrupt surfaces, as opposed to walking on rough terrains, demands the integration of proprioceptive and…

Robot simulation has been an essential tool for data-driven manipulation tasks. However, most existing simulation frameworks lack either efficient and accurate models of physical interactions with tactile sensors or realistic tactile…

Quadruped robots excel in traversing complex, unstructured environments where wheeled robots often fail. However, enabling efficient and adaptable locomotion remains challenging due to the quadrupeds' nonlinear dynamics, high degrees of…

We study sim-to-real skill transfer and discovery in the context of robotics control using representation learning. We draw inspiration from spectral decomposition of Markov decision processes. The spectral decomposition brings about…

Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…

For a robot to learn a good policy, it often requires expensive equipment (such as sophisticated sensors) and a prepared training environment conducive to learning. However, it is seldom possible to perfectly equip robots for economic…

Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow…

This paper tackles the task of goal-conditioned dynamic manipulation of deformable objects. This task is highly challenging due to its complex dynamics (introduced by object deformation and high-speed action) and strict task requirements…

Differentiable simulators provide analytic gradients, enabling more sample-efficient learning algorithms and paving the way for data intensive learning tasks such as learning from images. In this work, we demonstrate that locomotion…

This work presents a motion retargeting approach for legged robots, aimed at transferring the dynamic and agile movements to robots from source motions. In particular, we guide the imitation learning procedures by transferring motions from…

We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a…

Legged robots must adapt their gait to navigate unpredictable environments, a challenge that animals master with ease. However, most deep reinforcement learning (DRL) approaches to quadruped locomotion rely on a fixed gait, limiting…

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across…

Recently, reinforcement learning has become a promising and polular solution for robot legged locomotion. Compared to model-based control, reinforcement learning based controllers can achieve better robustness against uncertainties of…

Robot skill acquisition processes driven by reinforcement learning often rely on simulations to efficiently generate large-scale interaction data. However, the absence of simulation models for tactile sensors has hindered the use of tactile…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

In robots task and motion planning (TAMP), it is crucial to sample within the robot's configuration space to meet task-level global constraints and enhance the efficiency of subsequent motion planning. Due to the complexity of joint…

Training a deep network policy for robot manipulation is notoriously costly and time consuming as it depends on collecting a significant amount of real world data. To work well in the real world, the policy needs to see many instances of…

Sim-to-real discrepancies hinder learning-based policies from achieving high-precision tasks in the real world. While Domain Randomization (DR) is commonly used to bridge this gap, it often relies on heuristics and can lead to overly…