Zero-shot Deployment of a 5-Motor Bicycle Robot with Reinforcement Learning
零样本真机直跑!RAI研究所造出5电机自行车机器人:8米/秒、半秒空翻、1米跳台
Researchers from RAI Institute have developed a bicycle-shaped robot, UMV, capable of high-speed movement, jumps, and aerial flips using only five motors and reinforcement learning. The robot achieves 8 m/s speed, 1-meter jumps, and half-second aerial flips without specialized hardware for balance. Training occurs entirely in simulation, with zero-shot deployment to physical hardware. The study highlights the potential of reducing mechanical complexity and relying on learning algorithms for dynamic robotic tasks.
The paper presents a novel approach to mobile robotics by reducing mechanical complexity and relying on reinforcement learning for dynamic tasks. The UMV robot demonstrates zero-shot deployment from simulation to real-world performance, achieving high-speed movement, jumps, and aerial maneuvers without specialized hardware for stability.
Source: Chinese robotics — Research news discovery · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S15
Reported numbers
speed
8
View original evidence
最高行驶速度: 8 m/s(约 28.8 km/h),超过常规四足机器人的稳态巡航速度; 越障高度: 1 米,达到自身蹲伏高度的 130%; 连续可靠性: 15 次自主跳台测试,起跳阶段轨迹高度重合,波动只出现在落地冲击阶段。
Open source S22height
1
View original evidence
最高行驶速度: 8 m/s(约 28.8 km/h),超过常规四足机器人的稳态巡航速度; 越障高度: 1 米,达到自身蹲伏高度的 130%; 连续可靠性: 15 次自主跳台测试,起跳阶段轨迹高度重合,波动只出现在落地冲击阶段。
Open source S22reliability
15
View original evidence
最高行驶速度: 8 m/s(约 28.8 km/h),超过常规四足机器人的稳态巡航速度; 越障高度: 1 米,达到自身蹲伏高度的 130%; 连续可靠性: 15 次自主跳台测试,起跳阶段轨迹高度重合,波动只出现在落地冲击阶段。
Open source S22weight
23.5
height
0.8
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
训练全程在NVIDIA Isaac Lab 仿真环境中完成 ,思路和教小孩学骑车很像,摔了就重来,做对了给奖励。
Open source S15
最高行驶速度: 8 m/s(约 28.8 km/h),超过常规四足机器人的稳态巡航速度; 越障高度: 1 米,达到自身蹲伏高度的 130%; 连续可靠性: 15 次自主跳台测试,起跳阶段轨迹高度重合,波动只出现在落地冲击阶段。
Open source S22
整台机器人重23.5公斤,完全蹲伏时只有0.8米高。
Open source S10
一台23.5公斤的机器人在起跳瞬间的功率密度,接近一辆小型电动车的电机。
Open source S14
03. 七个月,几十次摔坏,换半秒空中翻转 论文里的实测数据,把这台极简机器人的能力拉到了非常直观的量级。
Open source S21
Source:Chinese robotics — Research news discovery · news.qq.com