DRAFTO: Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization for Robotic Manipulators

2026-03-10

AI Summary

This work addresses the challenges of low computational efficiency and difficulty in guaranteeing feasibility in robotic trajectory optimization due to joint limits, safety requirements, and task constraints. The authors propose a decoupled, dimensionality-reduced optimization framework that parameterizes trajectories using basis functions and formulates a constrained objective function incorporating smoothness, safety, joint limits, and task specifications. The optimization is decomposed into two stages: a main iteration using a reduced-dimension Gauss–Newton method and a feasibility-restoration phase based on constrained quadratic programming. By integrating hinge-squared penalties, an adaptive feasibility restoration mechanism, and a non-monotonic two-stage acceptance criterion, the approach significantly enhances global convergence and computational efficiency. Experiments demonstrate superior performance over state-of-the-art optimizers—including CHOMP, TrajOpt, GPMP2, and FACTO—as well as sampling-based planners like RRT-Connect across multiple benchmark tasks, with real-robot grasping experiments further validating its efficiency and reliability.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Optimization
• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

This paper introduces a new algorithm for trajectory optimization, Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization (DRAFTO). It first constructs a constrained objective that accounts for smoothness, safety, joint limits, and task requirements. Then, it optimizes the coefficients, which are the coordinates of a set of basis functions for trajectory parameterization. To reduce the number of repeated constrained optimizations while handling joint-limit feasibility, the optimization is decoupled into a reduced-space Gauss-Newton (GN) descent for the main iterations and constrained quadratic programming for initialization and terminal feasibility repair. The two-phase acceptance rule with a non-monotone policy is applied to the GN model, which uses a hinge-squared penalty for inequality constraints, to ensure globalizability. The results of our benchmark tests against optimization-based planners, such as CHOMP, TrajOpt, GPMP2, and FACTO, and sampling-based planners, such as RRT-Connect, RRT*, and PRM, validate the high efficiency and reliability across diverse scenarios and tasks. The experiment involving grabbing an object from a drawer further demonstrates the potential for implementation in complex manipulation tasks. The supplemental video is available at https://youtu.be/XisFI37YyTQ.

Problem

• trajectory optimization
• robotic manipulators
• joint limits
• feasibility
• constrained optimization

Innovation

• Decoupled Optimization
• Reduced-space Gauss-Newton
• Adaptive Feasibility Repair
• Hinge-squared Penalty
• Trajectory Parameterization