MAVP 框架用地图锚定提升移动操作机器人任务成功率
MAVP: Map-Aware Visuomotor Policies for Mobile Manipulation
机器人移动操作总因底盘跑偏而失败？这篇论文让策略直接预测地图坐标系下的底盘目标位姿再用定位反馈去跟踪，6 个真实任务成功率全赢速度控制，做具身智能的可以看看。
MAVP（Map-Aware Visuomotor Policies）框架从遥操作演示中重建静态地图，把演示的底盘轨迹统一到地图坐标系，为策略提供一致的空间监督。执行时策略接收 RGB 观测、关节状态和地图系底盘位姿，联合预测目标底盘位姿、手臂动作和夹爪动作，并由底层控制器用前馈运动和位姿误差反馈跟踪目标。训练中还引入位姿噪声增强，提升对位姿输入误差的鲁棒性。在 6 个真实操作任务和 3 类策略上，MAVP 的任务成功率在全部任务中均高于无锚定的速度控制方法。
MAVP: Map-Aware Visuomotor Policies for Mobile Manipulation
Successful mobile manipulation requires coordinated base and arm motion while maintaining accurate spatial positioning. However, demonstration-trained policies can struggle to realise the intended base motion reliably, leading to spatial misalignment and subsequent manipulation failures. We present MAVP (Map-Aware Visuomotor Policies), a framework that improves execution reliability by predicting explicit base-pose targets and tracking them using localisation feedback. MAVP reconstructs a static map from teleoperated demonstrations and expresses demonstrated base trajectories in a shared map frame, providing consistent spatial supervision across demonstrations. At execution time, the policy receives RGB observations, joint states, and the robot's current map-frame base pose, and jointly predicts target base poses, arm actions, and gripper actions. A low-level controller tracks the predicted base targets using feedforward motion and pose error feedback, enabling correction of execution deviations. We additionally use pose-noise augmentation during training to improve robustness to errors in the policy's pose input. Across six real-world manipulation tasks and three policy families, MAVP achieves higher task success rates than unanchored velocity control in all tasks. Videos and additional results are available at https://123qwedsa123.github.io/mavp/.
