| 1 |
The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption |
神经符号方法在长时程操作任务中优于VLA，且能耗显著降低 |
manipulation vision-language-action VLA |
|
|
| 2 |
WildOS: Open-Vocabulary Object Search in the Wild |
提出WildOS以解决复杂户外环境中的开放词汇物体搜索问题 |
legged robot open-vocabulary open vocabulary |
✅ |
|
| 3 |
Human-to-Robot Interaction: Learning from Video Demonstration for Robot Imitation |
提出一种模块化人机交互模仿学习框架，从视频演示中学习机器人操作技能。 |
manipulation reinforcement learning deep reinforcement learning |
✅ |
|
| 4 |
Design and Control of Modular Magnetic Millirobots for Multimodal Locomotion and Shape Reconfiguration |
设计模块化磁性微型机器人，实现多模态运动和形状重构 |
locomotion manipulation multimodal |
|
|
| 5 |
Vid2Sid: Videos Can Help Close the Sim2Real Gap |
Vid2Sid：利用视频弥合Sim2Real差距，实现物理参数自动标定与可解释性推理。 |
sim2real foundation model |
|
|
| 6 |
Visual Prompt Guided Unified Pushing Policy |
提出视觉提示引导的统一推物策略，提升机器人操作的泛化性和效率 |
manipulation flow matching multimodal |
|
|
| 7 |
Design, Locomotion, and Control of Amphibious Robots: Recent Advances |
综述两栖机器人设计、运动与控制的最新进展，助力环境监测与灾害应对。 |
locomotion |
|
|
| 8 |
Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization |
提出值引导的多路径反射方法，优化VLM在复杂机器人操作任务中的策略。 |
manipulation |
|
|
| 9 |
3D Shape Control of Extensible Multi-Section Soft Continuum Robots via Visual Servoing |
提出基于视觉伺服的可伸缩多节软体连续机器人的3D形状控制方法。 |
manipulation |
|
|