中文
相关论文

相关论文: Learning Sim-to-Real Humanoid Locomotion in 15 Min…

200 篇论文

Reinforcement learning (RL) has driven significant progress in robotics, but its complexity and long training times remain major bottlenecks. In this report, we introduce FastTD3, a simple, fast, and capable RL algorithm that significantly…

机器人学 · 计算机科学 2025-06-03 Younggyo Seo , Carmelo Sferrazza , Haoran Geng , Michal Nauman , Zhao-Heng Yin , Pieter Abbeel

Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibitively large number of training samples for learning complex tasks. Many recent works on speeding up Deep RL have focused on distributed training and simulation. While…

机器人学 · 计算机科学 2018-10-25 Jacky Liang , Viktor Makoviychuk , Ankur Handa , Nuttapong Chentanez , Miles Macklin , Dieter Fox

Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or adapting from pretrained policies remains rare, limiting the full potential of humanoid robots.…

机器人学 · 计算机科学 2025-08-27 Kaizhe Hu , Haochen Shi , Yao He , Weizhuo Wang , C. Karen Liu , Shuran Song

Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust training via large-scale parallel simulation and, in some cases, zero-shot deployment to real…

机器人学 · 计算机科学 2026-02-24 Weidong Huang , Zhehan Li , Hangxin Liu , Biao Hou , Yao Su , Jingwen Zhang

Learning generalizable robot manipulation policies, especially for complex multi-fingered humanoids, remains a significant challenge. Existing approaches primarily rely on extensive data collection and imitation learning, which are…

机器人学 · 计算机科学 2025-09-03 Toru Lin , Kartik Sachdev , Linxi Fan , Jitendra Malik , Yuke Zhu

Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tuning these policies directly on hardware is problematic, as it poses risks of mechanical failure and…

机器人学 · 计算机科学 2026-03-19 Elham Daneshmand , Shafeef Omar , Glen Berseth , Majid Khadiv , Hsiu-Chin Lin

Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning…

机器人学 · 计算机科学 2025-05-13 Benedict Hildisch , Edoardo Ghignone , Nicolas Baumann , Cheng Hu , Andrea Carron , Michele Magno

Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly…

Humanoid robots have the promise of locomoting like humans, including fast and dynamic running. Recently, reinforcement learning (RL) controllers that can mimic human motions have become popular as they can generate very dynamic behaviors,…

机器人学 · 计算机科学 2026-03-30 Zachary Olkin , William D. Compton , Ryan M. Bena , Aaron D. Ames

Learning-based methods, particularly Reinforcement Learning (RL), hold great promise for streamlining deployment, enhancing performance, and achieving generalization in the control of autonomous multirotor aerial vehicles. Deep RL has been…

机器人学 · 计算机科学 2024-04-10 Jonas Eschmann , Dario Albani , Giuseppe Loianno

For the deployment of legged robots in real-world environments, it is essential to develop robust locomotion control methods for challenging terrains that may exhibit unexpected deformability and irregularity. In this paper, we explore the…

机器人学 · 计算机科学 2025-04-21 Rohan P. Singh , Mitsuharu Morisawa , Mehdi Benallegue , Zhaoming Xie , Fumio Kanehiro

Recent breakthroughs in the reinforcement learning (RL) community have made significant advances towards learning and deploying policies on real world robotic systems. However, even with the current state-of-the-art algorithms and…

机器人学 · 计算机科学 2019-03-07 Guillaume Bellegarda , Katie Byl

In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation…

机器学习 · 计算机科学 2025-11-12 Haoxiang You , Yilang Liu , Ian Abraham

Visual reinforcement learning is appealing for robotics but expensive -- off-policy methods are sample-efficient yet slow; on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster…

机器人学 · 计算机科学 2026-02-25 Abdulaziz Almuzairee , Henrik I. Christensen

Achieving highly dynamic humanoid parkour on unseen, complex terrains remains a challenge in robotics. Although general locomotion policies demonstrate capabilities across broad terrain distributions, they often struggle with arbitrary and…

机器人学 · 计算机科学 2026-02-03 Shaoting Zhu , Baijun Ye , Jiaxuan Wang , Jiakang Chen , Ziwen Zhuang , Linzhan Mou , Runhan Huang , Hang Zhao

Humanoid locomotion is a key skill to bring humanoids out of the lab and into the real-world. Many motion generation methods for locomotion have been proposed including reinforcement learning (RL). RL locomotion policies offer great…

机器人学 · 计算机科学 2024-07-09 William Thibault , William Melek , Katja Mombaur

Whole-body humanoid locomotion is challenging due to high-dimensional control, morphological instability, and the need for real-time adaptation to various terrains using onboard perception. Directly applying reinforcement learning (RL) with…

Designing agile locomotion for quadruped robots often requires extensive expertise and tedious manual tuning. In this paper, we present a system to automate this process by leveraging deep reinforcement learning techniques. Our system can…

机器人学 · 计算机科学 2018-05-18 Jie Tan , Tingnan Zhang , Erwin Coumans , Atil Iscen , Yunfei Bai , Danijar Hafner , Steven Bohez , Vincent Vanhoucke

In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of different training…

机器人学 · 计算机科学 2022-08-22 Nikita Rudin , David Hoeller , Philipp Reist , Marco Hutter

Recent advances in deep reinforcement learning (RL) based techniques combined with training in simulation have offered a new approach to developing robust controllers for legged robots. However, the application of such approaches to real…

机器人学 · 计算机科学 2023-08-08 Rohan Pratap Singh , Zhaoming Xie , Pierre Gergondet , Fumio Kanehiro
‹ 上一页 1 2 3 10 下一页 ›