Related papers: Data-Driven Latent Space Representation for Robust…
Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the…
Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL,…
Designing control policies for legged locomotion is complex due to the under-actuated and non-continuous robot dynamics. Model-free reinforcement learning provides promising tools to tackle this challenge. However, a major bottleneck of…
Traditionally, model-based reinforcement learning (MBRL) methods exploit neural networks as flexible function approximators to represent $\textit{a priori}$ unknown environment dynamics. However, training data are typically scarce in…
While Reinforcement Learning (RL) has achieved remarkable progress in legged locomotion control, it often suffers from performance degradation in out-of-distribution (OOD) conditions and discrepancies between the simulation and the real…
Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward…
We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide…
Humanoid robots have demonstrated robust locomotion capabilities using Reinforcement Learning (RL)-based approaches. Further, to obtain human-like behaviors, existing methods integrate human motion-tracking or motion prior in the RL…
Achieving robust locomotion on complex terrains remains a challenge due to high dimensional control and environmental uncertainties. This paper introduces a teacher prior framework based on the teacher student paradigm, integrating…
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.…
Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robot. In contrast, approximate reduced-order models are…
Robot motor skills can be learned through deep reinforcement learning (DRL) by neural networks as state-action mappings. While the selection of state observations is crucial, there has been a lack of quantitative analysis to date. Here, we…
Deep reinforcement learning produces robust locomotion policies for legged robots over challenging terrains. To date, few studies have leveraged model-based methods to combine these locomotion skills with the precise control of…
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a DeepMDP, a parameterized…
Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of joint freedom and force limits, exact replication of human…
To proactively navigate and traverse various terrains, active use of visual perception becomes indispensable. We aim to investigate the feasibility and performance of using sparse visual observations to achieve perceptual locomotion over a…
Estimating the state of an environment from high-dimensional, multimodal, and noisy observations is a fundamental challenge in reinforcement learning (RL). Traditional approaches rely on probabilistic models to account for the uncertainty,…
Model predictive control (MPC) has demonstrated effectiveness for humanoid bipedal locomotion; however, its applicability in challenging environments, such as rough and slippery terrain, is limited by the difficulty of modeling terrain…
Previous studies have successfully demonstrated agile and robust locomotion in challenging terrains for quadrupedal robots. However, the bipedal locomotion mode for quadruped robots remains unverified. This paper explores the adaptation of…
Legged robots are becoming increasingly powerful and popular in recent years for their potential to bring the mobility of autonomous agents to the next level. This work presents a deep reinforcement learning approach that learns a robust…