| 1 |
Observer Actor: Active Vision Imitation Learning with Sparse View Gaussian Splatting |
提出Observer Actor框架，通过主动视觉模仿学习提升双臂机器人的操作性能。 |
dual-arm imitation learning behavior cloning |
|
|
| 2 |
Switch-JustDance: Benchmarking Whole Body Motion Tracking Policies Using a Commercial Console Game |
提出Switch-JustDance：利用商业游戏评估全身运动跟踪策略的低成本基准测试方案 |
legged robot humanoid whole-body control |
|
|
| 3 |
Off-Road Navigation via Implicit Neural Representation of Terrain Traversability |
提出TRAIL：利用隐式神经表示进行地形可通行性评估的越野导航框架 |
trajectory optimization traversability navigation |
|
|
| 4 |
EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation |
EchoVLA：面向移动操作的协同声明式记忆机器人视觉-语言-动作模型 |
manipulation mobile manipulation navigation |
|
|
| 5 |
A Coordinated Dual-Arm Framework for Delicate Snap-Fit Assemblies |
提出SnapNet与双臂协调框架，解决精密卡扣装配中的力控与检测问题 |
bi-manual bimanual dual-arm |
|
|
| 6 |
Time-aware Motion Planning in Dynamic Environments with Conformal Prediction |
提出基于Conformal Prediction的时间感知运动规划框架，解决动态环境中安全导航问题。 |
motion planning navigation |
|
|
| 7 |
RoboArmGS: High-Quality Robotic Arm Splatting via Bézier Curve Refinement |
RoboArmGS：基于贝塞尔曲线优化的高质量机械臂高斯溅射 |
sim2real real2sim |
|
|
| 8 |
Continually Evolving Skill Knowledge in Vision Language Action Model |
Stellar VLA：面向视觉-语言-动作模型的知识驱动持续学习框架 |
manipulation |
|
|