Visibility-Aware Mobile Grasping in Dynamic Environments

2026-05-04

AI Summary

This work addresses the perception-action trade-off and collision risks inherent in mobile manipulation within dynamically changing, partially observable environments. The authors propose a unified framework that integrates high-level task planning via behavior trees with iterative whole-body motion planning at the low level. A key innovation lies in the introduction of a velocity-aware active perception mechanism coupled with an adaptive sub-goal generation strategy, enabling joint optimization of perception, motion, and task objectives. Evaluated across 400 randomized simulated and real-world scenarios, the system achieves success rates of 68.8% and 58.0% in static and dynamic unknown environments, respectively—representing improvements of 22.8% and 18.0% over baseline methods—and demonstrates significantly enhanced safety and task completion reliability.

Abstract

This paper addresses the problem of mobile grasping in dynamic, unknown environments where a robot must operate under a limited field-of-view. The fundamental challenge is the inherent trade-off between ``seeing'' around to reduce environmental uncertainty and ``moving'' the body to achieve task progress in a high-dimensional configuration space, subject to visibility constraints. Previous approaches often assume known or static environments and decouple these objectives, failing to guarantee safety when unobserved dynamic obstacles intersect the robot's path during manipulation. In this paper, we propose a unified mobile grasping system comprising two core components: (1) an iterative low-level whole-body planner coupled with velocity-aware active perception to navigate dynamic environments safely; and (2) a hierarchical high-level planner based on behavior trees that adaptively generates subgoals to guide the robot through exploration and runtime failures. We provide experimental results across 400 randomized simulation scenarios and real-world deployment on a Fetch mobile manipulator. Results show that our system achieves a success rate of 68.8\% and 58.0\% in unknown static and dynamic environments, respectively, significantly boosting success rates by 22.8\% and 18.0\% over the \nam approach in both unknown static and dynamic environments, with improved collision safety.

Problem

• mobile grasping
• dynamic environments
• visibility constraints
• field-of-view limitation
• safety guarantee

Innovation

• mobile grasping
• active perception
• whole-body planning
• behavior trees
• dynamic environments