ToMPC: Task-oriented Model Predictive Control via ADMM for Safe Robotic Manipulation

2026-03-14

AI Summary

This work addresses the challenge of achieving safe and efficient robotic manipulation in obstacle-dense open workspaces by proposing a task-oriented model predictive control framework. The approach decomposes the complex optimization problem into motion planning and force control subproblems via the Alternating Direction Method of Multipliers (ADMM), which are efficiently solved using Differential Dynamic Programming (DDP) and Quadratic Programming (QP), respectively. By integrating a task-driven obstacle avoidance mechanism with kinematic redundancy, the framework unifies motion and force control to rigorously satisfy hard safety constraints. Experimental validation on a Franka Panda manipulator demonstrates that the proposed method generates, in real time, collision-free trajectories that maximize operational range while ensuring safety and task performance.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper proposes a task-oriented model predictive control (ToMPC) framework for safe and efficient robotic manipulation in open workspaces. The framework unifies collision-free motion and robot-environment interaction to address diverse scenarios. Additionally, it introduces task-oriented obstacle avoidance that leverages kinematic redundancy to enhance manipulation efficiency in obstructed environments. This complex optimization problem is solved by the alternating direction method of multipliers (ADMM), which decomposes the problem into two subproblems tackled by differential dynamic programming (DDP) and quadratic programming (QP), respectively. The effectiveness of this approach is validated in simulation and hardware experiments on a Franka Panda robotic manipulator. Results demonstrate that the framework can plan motion and/or force trajectories in real time, maximize the manipulation range while avoiding obstacles, and strictly adhere to safety-related hard constraints.

Problem

• robotic manipulation
• collision avoidance
• task-oriented control
• safety constraints
• obstacle-rich environments

Innovation

• Task-oriented MPC
• ADMM
• Kinematic redundancy
• Obstacle avoidance
• Safe robotic manipulation