A Task-Driven, Planner-in-the-Loop Computational Design Framework for Modular Manipulators

2025-12-17

AI Summary

Joint optimization of configuration, mounting pose, and trajectory for modular manipulators is challenging; single-chain extensions often exceed joint torque limits. Method: This paper proposes a task-driven closed-loop design framework featuring a novel “planner-in-the-loop” paradigm. It introduces virtual module abstractions to enable dual-chain configurations, where an auxiliary chain offloads payload from the primary chain—expanding workspace without increasing module power ratings. The framework integrates hierarchical model predictive control (HMPC), covariance matrix adaptation evolution strategy (CMA-ES), and hybrid-space (discrete + continuous) co-optimization. Results: Validated on polishing, drilling, and grasping tasks, the method generates multiple feasible designs satisfying kinematic, dynamic, and physical constraints. It supports customizable objectives—including minimal joint torque and maximal manipulability—and achieves large-workspace dual-chain configurations with significantly reduced base torque.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Modular manipulators composed of pre-manufactured and interchangeable modules offer high adaptability across diverse tasks. However, their deployment requires generating feasible motions while jointly optimizing morphology and mounted pose under kinematic, dynamic, and physical constraints. Moreover, traditional single-branch designs often extend reach by increasing link length, which can easily violate torque limits at the base joint. To address these challenges, we propose a unified task-driven computational framework that integrates trajectory planning across varying morphologies with the co-optimization of morphology and mounted pose. Within this framework, a hierarchical model predictive control (HMPC) strategy is developed to enable motion planning for both redundant and non-redundant manipulators. For design optimization, the CMA-ES is employed to efficiently explore a hybrid search space consisting of discrete morphology configurations and continuous mounted poses. Meanwhile, a virtual module abstraction is introduced to enable bi-branch morphologies, allowing an auxiliary branch to offload torque from the primary branch and extend the achievable workspace without increasing the capacity of individual joint modules. Extensive simulations and hardware experiments on polishing, drilling, and pick-and-place tasks demonstrate the effectiveness of the proposed framework. The results show that: 1) the framework can generate multiple feasible designs that satisfy kinematic and dynamic constraints while avoiding environmental collisions for given tasks; 2) flexible design objectives, such as maximizing manipulability, minimizing joint effort, or reducing the number of modules, can be achieved by customizing the cost functions; and 3) a bi-branch morphology capable of operating in a large workspace can be realized without requiring more powerful basic modules.

Problem

• Optimizing modular manipulator morphology and pose under constraints
• Enabling large workspace without increasing joint torque limits
• Generating feasible motion plans for diverse tasks efficiently

Innovation

• Hierarchical MPC enables motion planning for redundant and non-redundant manipulators.
• CMA-ES optimizes discrete morphology and continuous mounted pose in hybrid search space.
• Virtual module abstraction allows bi-branch morphologies to offload torque and extend workspace.