A Solution to Adaptive Mobile Manipulator Throwing

TL;DR

This paper presents a fast, adaptive method for mobile manipulator throwing that simplifies the problem to a planar case and uses machine learning to generate feasible throws within milliseconds, enabling real-time replanning.

Contribution

It introduces a novel simplified planar approach combined with machine learning for rapid, adaptive throwing motion planning in mobile manipulators.

Findings

Planning time reduced to 1 ms per query

System adapts to disturbances via real-time replanning

Method significantly improves efficiency and flexibility

Abstract

Mobile manipulator throwing is a promising method to increase the flexibility and efficiency of dynamic manipulation in factories. Its major challenge is to efficiently plan a feasible throw under a wide set of task specifications. We show that the mobile manipulator throwing problem can be simplified to a planar problem, hence greatly reducing the computational costs. Using machine learning approaches, we build a model of the object's inverted flying dynamics and the robot's kinematic feasibility, which enables throwing motion generation within 1 ms for given query of target position. Thanks to the computational efficiency of our method, we show that the system is adaptive under disturbance, via replanning on the fly for alternative solutions, instead of sticking to the original throwing plan.