| 1 |
SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor Learning |
提出SLIM，通过纯模拟强化学习训练低成本四足机器人完成长时程操作任务。 |
quadruped locomotion locomotion policy |
|
|
| 2 |
Learning More With Less: Sample Efficient Model-Based RL for Loco-Manipulation |
提出基于贝叶斯神经网络的Model-Based RL方法，高效解决Loco-Manipulation控制问题 |
quadruped legged locomotion locomotion |
|
|
| 3 |
DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation |
DexForce：从触觉示教中提取力感知的动作，用于灵巧操作 |
manipulation dexterous manipulation policy learning |
|
|
| 4 |
SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning |
SpatialCoT：通过坐标对齐和思维链提升具身任务规划中的空间推理能力 |
manipulation embodied AI chain-of-thought |
|
|
| 5 |
Early Failure Detection in Autonomous Surgical Soft-Tissue Manipulation via Uncertainty Quantification |
提出基于不确定性量化的手术软组织操作早期失败检测方法 |
manipulation bi-manual sim2real |
|
|
| 6 |
Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics |
提出一种基于神经网络模拟器的机器人世界模型，用于鲁棒策略优化。 |
sim-to-real reinforcement learning world model |
|
|
| 7 |
Tethered Variable Inertial Attitude Control Mechanisms through a Modular Jumping Limbed Robot |
提出一种基于系绳可变惯性姿态控制的模块化跳跃机器人，用于低重力行星探索。 |
quadruped MPC model predictive control |
|
|