Bridging Discrete Planning and Continuous Execution for Redundant Robot

2026-04-02

AI Summary

This work addresses the challenges of directly executing discretely planned paths on 7-degree-of-freedom redundant manipulators, which often suffer from step-size jitter, abrupt joint transitions, and instability near singular configurations. The authors propose a smoothing execution framework that operates without modifying the original planner. By leveraging a 26-neighbor Cartesian action space combined with step-size normalization and a geometric symmetry-breaking mechanism, path oscillations are effectively suppressed. A task-priority damped least squares (TP-DLS) inverse kinematics layer is introduced, prioritizing end-effector position as the primary task while embedding orientation and joint-centering objectives in the null space as secondary tasks. Experimental results in cluttered environments demonstrate significant improvements: planning success rate increases from 0.58 to 1.00, path length reduces from 1.53 m to 1.10 m, end-effector error remains below 1 mm, and peak joint acceleration decreases by over an order of magnitude.

Abstract

Voxel-grid reinforcement learning is widely adopted for path planning in redundant manipulators due to its simplicity and reproducibility. However, direct execution through point-wise numerical inverse kinematics on 7-DoF arms often yields step-size jitter, abrupt joint transitions, and instability near singular configurations. This work proposes a bridging framework between discrete planning and continuous execution without modifying the discrete planner itself. On the planning side, step-normalized 26-neighbor Cartesian actions and a geometric tie-breaking mechanism are introduced to suppress unnecessary turns and eliminate step-size oscillations. On the execution side, a task-priority damped least-squares (TP-DLS) inverse kinematics layer is implemented. This layer treats end-effector position as a primary task, while posture and joint centering are handled as subordinate tasks projected into the null space, combined with trust-region clipping and joint velocity constraints. On a 7-DoF manipulator in random sparse, medium, and dense environments, this bridge raises planning success in dense scenes from about 0.58 to 1.00, shortens representative path length from roughly 1.53 m to 1.10 m, and while keeping end-effector error below 1 mm, reduces peak joint accelerations by over an order of magnitude, substantially improving the continuous execution quality of voxel-based RL paths on redundant manipulators.

Problem

• redundant manipulator
• discrete planning
• continuous execution
• inverse kinematics
• voxel-grid reinforcement learning

Innovation

• voxel-grid reinforcement learning
• task-priority inverse kinematics
• redundant manipulator
• discrete-to-continuous bridging
• damped least-squares