V
主页
ETH 最新Science Robotics基于学习的轮腿机器人自主导航和运动
发布人
https://youtu.be/eEsd10cirqM Learning robust autonomous navigation and locomotion for wheeled-legged robots ABSTRACT Autonomous wheeled-legged robots have the potential to transform logistics systems, improving operational efficiency and adaptability in urban environments. Navigating urban environments,however, poses unique challenges for robots, necessitating innovative solutions for locomotion and navigation. These challenges include the need for adaptive locomotion across varied terrains and the ability to navigate efficiently around complex dynamic obstacles. This work introduces a fully integrated system comprising adaptive locomotion control, mobility-aware local navigation planning, and large-scale path planning within the city. Using model-free reinforcement learning (RL) techniques and privileged learning, we develop a versatile locomotion controller. This controller achieves efficient and robust locomotion over various rough terrains, facilitated by smooth transitions between walking and driving modes. It is tightly integrated with a learned navigation controller through a hierarchical RL framework, enabling effective navigation through challenging terrain and various obstacles at high speed. Our controllers are integrated into a largescale urban navigation system and validated by autonomous, kilometer-scale navigation missions conducted in Zurich, Switzerland, and Seville, Spain. These missions demonstrate the system’s robustness and adaptability, underscoring the importance of integrated control systems in achieving seamless navigation in complex environments. Our findings support the feasibility of wheeled-legged robots and hierarchical RL for autonomous navigation, with implications for lastmile delivery and beyond. https://www.science.org/doi/10.1126/scirobotics.adi9641
打开封面
下载高清视频
观看高清视频
视频下载器
How to design nonlinear MPC with deep learning prediction model
[自制]手搓双足机器人样机demo|model-based控制|落后轻喷
Agile Continuous Jumping in Discontinuous Terrains
(Humanoid)An IntegratedForceSensitive, Impedance Controlled, Tendon-Driven Wrist
人形机器人3d 打印手臂 网址在简介 欢迎关注三连
(Humanoids 2023) Learning Safer Footstep Planning Policies for Legged Robots
【超多模型MPC算法】开源Mujoco-MPC演示
Deep Compliant Control for Legged Robots
dreamWaq复现尝试
(ICRA 2024) Actor-Critic Model Predictive Control
人形机器人腿部结构 基于 4DoF 球面并联机构
Tailoring model complexity in MPC of legged locomotion
人形机器人足底机械结构设计
(ICRA 24)A Lightweight Free-Climbing Robot for Extreme Terrain Exploration
人形机器人灵巧手臂最新成果
【破解深度学习】2.1 向量实现高维空间表达,张量实现多重复杂映射
Tutorial - Crocoddyl - Nicolas Mansard
Boston Dynamics Stretch at MODEX 2024
Reinforcement learning for blind stair climbing with legged and wheeled robot
The MIT Humanoid Robot Design Motion Planning and Control ForAcrobatic Behaviors
ETH 最新RL成果,已开源!SMUG 规划器:适用于具有挑战性环境下的移动机器人的安全多目标规划器
[24 T-RO]Hybrid iLQR MPC for Contact Implicit Stabilization on Legged Robots
人形机器人远程视觉操纵 论文和代码在简介
模型预测控制 (MPC) 从推导到C++ 实现,详细教程 仅使用 Eigen 库 代码在简介
DTC: Deep Tracking Control 4
Generalizing and improving regularized predictive control for legged robots
移动机械臂让土木工程焕发第二春
[IROS 2024] 通过分布式优化加速腿式机器人的模型预测控制
云深处发布托马斯回旋风火轮足机器人
understanding reinforcement learning environment and rewards
Implementing Torque Control-Based Biped Walking of Humanoid Robots
印度的四足机器人 看着还可以哦
Part 3 (Final) - How to Solve Inverse Kinematics of a 4 Leg Robot
真牛!这个人形机器人吊打很多厂家的“产品”
波士顿动力 四足机器人Spot-工业检测机器人解决方案-化工厂场景
Fatrop 求解器 完胜 IPOPT
reinforcement learning policies and learning algorithms
有开源github代码! RA-L论文 人形机器人的多接触全身控制
CASBOT 01,开启人机共生未来景观
单腿站立 轻轻松松 Atlas KarateKid