Human Motion Intent Inferencing in Teleoperation through a SINDy Paradigm
Michael Bowman, Xiaoli Zhang
AI summary
Problem
Current intent inference methods overlook subtle, discontinuous human motions like sudden jumps or hesitations, making it difficult to detect existing goals or discover new ones in unstructured teleoperation environments.
Approach
The framework models operator motion with a jump-drift-diffusion stochastic differential equation, estimates its dynamics using Kramers-Moyal coefficients, and applies Sparse Identification of Nonlinear Dynamics (SINDy) to infer goal transitions and predict future states.
Key results
- Novel jump-drift-diffusion motion model inferred via SINDy regression
- Statistical outlier detection algorithm paired with jump identification for goal discovery
- Probabilistic reachability sets for predicting operator motion bounds
- Validated feasibility on 600 offline and online teleoperation trajectories
Why it matters
Provides a robust, interpretable framework for shared control systems to anticipate human intent shifts and reduce cognitive load in unstructured robotic tasks.
Abstract
Intent inferencing in teleoperation has been instrumental in aligning operator goals and coordinating actions with robotic partners. However, current intent inference methods often ignore subtle motion that can be strong indicators for a sudden change in intent. Specifically, we aim to tackle 1) if we can detect sudden jumps in operator trajectories, 2) how to appropriately use these sudden jump motions to infer an operator’s goal state, and 3) how to incorporate these discontinuous and continuous dynamics to infer operator motion. Our framework, called Psychic, models these small indicative motions through a jump-drift-diffusion stochastic differential equation to cover discontinuous and continuous dynamics. Kramers-Moyal (KM) coefficients allow us to detect jumps with a trajectory which we pair with a statistical outlier detection algorithm to nominate goal transitions. Through identifying jumps, we can perform early detection of existing goals and discover undefined goals in unstructured scenarios. Our framework then applies a Sparse Identification of Nonlinear Dynamics (SINDy) model using KM coefficients with the goal transitions as a control input to infer an operator’s motion behavior in unstructured scenarios. We demonstrate Psychic can produce probabilistic reachability sets and compare our strategy to a negative log-likelihood model fit. We perform a retrospective study on 600 operator trajectories in a hands-free teleoperation task to evaluate the efficacy of our opensource package, Psychic, in both offline and online learning.