Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Human-Robotic Prosthesis as Collaborating Agents for Symmetrical Walking
Ruofan Wu, Junmin Zhong, Brent Abraham Wallace, Xiang Gao, He Huang, Jennie Si
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Include estimated human control influence in robot control (ablation) | cMARL · Level ground walking, OpenSim | stage cost: 0.008 -> 0.002 | Improved |
| Include estimated human control influence (ablation) | cMARL · Level ground walking, OpenSim | peak knee error: 0.007 -> 0.003 | Improved |
| Include estimated human control influence (ablation) | cMARL · Level ground walking, OpenSim | step length symmetry error: 0.006 -> 0.001 | Improved |
| Include estimated human control influence (ablation) | cMARL · Level ground walking, OpenSim | convergence steps: 187.5 -> 97 | Improved |
| Include estimated human control influence (ablation) | cMARL · Level ground walking, OpenSim | success rate: 0.58 -> 0.7 | Improved |
| Use cMARL instead of COMA | cMARL · Level ground walking, OpenSim | stage cost: 0.004 -> 0.002 | Improved |
| Use cMARL instead of COMA | cMARL · Level ground walking, OpenSim | peak knee error: 0.003 -> 0.003 | No clear effect |
| Use cMARL instead of COMA | cMARL · Level ground walking, OpenSim | success rate: 0.5 -> 0.7 | Improved |
| Use cMARL instead of COMA | cMARL · Level ground walking, OpenSim | convergence steps: 136 -> 97 | Improved |
| Use cMARL instead of MADDPG | cMARL · Level ground walking, OpenSim | stage cost: 0.38 -> 0.002 | Improved |
| Use cMARL instead of MADDPG | cMARL · Level ground walking, OpenSim | step length symmetry error: 0.022 -> 0.001 | Improved |
| Use cMARL instead of benchmarks | cMARL · Level ground walking, OpenSim | environment samples: at least 30% less | Improved |
Closest papers by meaning
- Reinforcement Learning Control of a Physical Robot Device for Assisted Human Walking without a Simulator (ICML 2025 · similarity 0.87)
- Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes (AAAI 2025 · similarity 0.86)
- CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning (ICLR 2024 · similarity 0.86)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.85)
- Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.85)
- POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
