Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Trajectory Optimization for Task-Specific Human-Robot Collaboration

Hamed Rahimi Nohooji, Holger Voos

TL;DR

The paper tackles the need for real-time, task-specific human-robot collaboration without fixed reference trajectories. It introduces an integrated pipeline that uses the inverse differential Riccati equation to generate adaptive trajectories from a human-impedance–robot-compliance model and couples it with a neuro-adaptive PID controller that adjusts neural gains online for stable, accurate tracking. Key contributions include a unified HRC framework, time-varying impedance modeling, and a low-cost adaptive control strategy with Lyapunov guarantees, demonstrated by a two-link simulation. The approach enables safe, efficient collaboration in dynamic environments by continuously aligning plan and control to human input while maintaining real-time feasibility. The work lays a foundation for practical HRC systems with plug-in trajectory optimization and robust, adaptive control, with future directions toward experimental validation and extension to more complex tasks.

Abstract

This paper proposes a task-specific trajectory optimization framework for human-robot collaboration, enabling adaptive motion planning based on human interaction dynamics. Unlike conventional approaches that rely on predefined desired trajectories, the proposed framework optimizes the collaborative motion dynamically using the inverse differential Riccati equation, ensuring adaptability to task variations and human input. The generated trajectory serves as the reference for a neuro-adaptive PID controller, which leverages a neural network to adjust control gains in real time, addressing system uncertainties while maintaining low computational complexity. The combination of trajectory planning and the adaptive control law ensures stability and accurate joint-space tracking without requiring extensive parameter tuning. Numerical simulations validate the proposed approach.

Adaptive Trajectory Optimization for Task-Specific Human-Robot Collaboration

TL;DR

The paper tackles the need for real-time, task-specific human-robot collaboration without fixed reference trajectories. It introduces an integrated pipeline that uses the inverse differential Riccati equation to generate adaptive trajectories from a human-impedance–robot-compliance model and couples it with a neuro-adaptive PID controller that adjusts neural gains online for stable, accurate tracking. Key contributions include a unified HRC framework, time-varying impedance modeling, and a low-cost adaptive control strategy with Lyapunov guarantees, demonstrated by a two-link simulation. The approach enables safe, efficient collaboration in dynamic environments by continuously aligning plan and control to human input while maintaining real-time feasibility. The work lays a foundation for practical HRC systems with plug-in trajectory optimization and robust, adaptive control, with future directions toward experimental validation and extension to more complex tasks.

Abstract

This paper proposes a task-specific trajectory optimization framework for human-robot collaboration, enabling adaptive motion planning based on human interaction dynamics. Unlike conventional approaches that rely on predefined desired trajectories, the proposed framework optimizes the collaborative motion dynamically using the inverse differential Riccati equation, ensuring adaptability to task variations and human input. The generated trajectory serves as the reference for a neuro-adaptive PID controller, which leverages a neural network to adjust control gains in real time, addressing system uncertainties while maintaining low computational complexity. The combination of trajectory planning and the adaptive control law ensures stability and accurate joint-space tracking without requiring extensive parameter tuning. Numerical simulations validate the proposed approach.
Paper Structure (8 sections, 2 theorems, 29 equations, 6 figures, 1 algorithm)

This paper contains 8 sections, 2 theorems, 29 equations, 6 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Modeling and Problem Definition
  3. System Description
  4. Problem Statement
  5. Task-Specific Assistive Human-Robot Collaboration
  6. Robot-Specific Control Design
  7. Simulation Study
  8. Discussion and Conclusion

Key Result

Lemma 1

chen2021tracking Given the commutative variable $e_c(t)$ in eq:E1, if $e_c(t) \to 0$ as $t \to \infty$, then the tracking errors $e(t)$, $\dot{e}(t)$, and their integrals are bounded and converge to zero as time progresses.

Figures (6)

  • Figure 1: Cartesian trajectory in the $XY$ plane.
  • Figure 2: Positions in the Cartesian space: $x_\mathrm{imp}$ and $y_\mathrm{imp}$.
  • Figure 3: Interaction force $f_h$ during human-robot collaboration.
  • Figure 4: Desired and actual trajectories for the first joint.
  • Figure 5: Desired and actual trajectories for the second joint.
  • ...and 1 more figures

Theorems & Definitions (3)

  • Lemma 1
  • Lemma 2
  • proof