Task-Driven Co-Design of Mobile Manipulators

2024-12-21

arXiv.org

AI Summary

Existing mobile manipulators typically employ desktop-mounted static arms, which lack the operational workspace and height adaptability required for domestic tasks such as opening hinged doors, resulting in severe kinematic constraints. Method: This paper proposes the first task-driven co-design framework for mobile manipulators, jointly optimizing both the arm mounting parameters and the mobile base pose. We introduce a novel two-level paradigm: an inner-loop reinforcement learning policy for control training, coupled with outer-loop BOHB hyperparameter optimization, integrated with physics-aware feasibility modeling and modular design principles. Contribution/Results: The generated configurations significantly improve performance on both seen and unseen tasks—outperforming heuristic metric-based designs. All solutions are constructed exclusively from off-the-shelf components, ensuring low cost, manufacturability, and plug-and-play modularity.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recent interest in mobile manipulation has resulted in a wide range of new robot designs. A large family of these designs focuses on modular platforms that combine existing mobile bases with static manipulator arms. They combine these modules by mounting the arm in a tabletop configuration. However, the operating workspaces and heights for common mobile manipulation tasks, such as opening articulated objects, significantly differ from tabletop manipulation tasks. As a result, these standard arm mounting configurations can result in kinematics with restricted joint ranges and motions. To address these problems, we present the first Concurrent Design approach for mobile manipulators to optimize key arm-mounting parameters. Our approach directly targets task performance across representative household tasks by training a powerful multitask-capable reinforcement learning policy in an inner loop while optimizing over a distribution of design configurations guided by Bayesian Optimization and HyperBand (BOHB) in an outer loop. This results in novel designs that significantly improve performance across both seen and unseen test tasks, and outperform designs generated by heuristic-based performance indices that are cheaper to evaluate but only weakly correlated with the motions of interest. We evaluate the physical feasibility of the resulting designs and show that they are practical and remain modular, affordable, and compatible with existing commercial components. We open-source the approach and generated designs to facilitate further improvements of these platforms.

Problem

• Optimizing arm-mounting parameters for mobile manipulators
• Improving task performance in household manipulation tasks
• Designing modular, affordable robots with commercial components

Innovation

• Concurrent Design optimizes arm-mounting parameters
• Reinforcement learning trains multitask policy
• Bayesian Optimization guides design configurations