Method adapts robot control by reading human intent during remote tasks
Intent-Informed Model Predictive Control for Shared Autonomy in Remote Manipulation Tasks
Robotics
Summary
Controlling robots from a distance can be tricky because sometimes humans want full control, and other times they want the robot to take over more. This paper presents a way to smoothly adjust how much control a human or a robot has by guessing what the human wants based on where they look and how they move the robot arm. The method uses this guess to blend human and robot control smartly, making remote manipulation faster and easier. Experiments showed that this approach saves time and effort while users felt in control and less tired.
What this means in practice
- •For robotic teleoperators: Improve remote object manipulation by dynamically blending human and robot control using real-time intent from gaze and motion data.
- •For industrial robot integrators: Design robot systems that adjust autonomy levels seamlessly based on operator intent for safer and more efficient remote handling tasks.
Authors
Lorena Maria Genua, Camilla Tabasso, Mya Schroder, Joshua Migdal, Tye Brady, Taskin Padir
Abstract
Shared autonomy is a control paradigm that combines human cognitive abilities with robot precision to enable effective remote manipulation in complex environments. A key challenge is how to adapt the level of autonomy using information extracted from the human, task, and/or environment. In this paper, we propose a novel arbitration strategy that dynamically adjusts the level of autonomy in the system using the entropy of a belief distribution derived from a multimodal intent inference. Human intent is modeled with a Dynamic Bayesian Network (DBN), which updates beliefs over goals given real-time operator gaze data and robot arm motion during teleoperation. We then formulate the blending of human input and autonomous control as a Model Predictive Control (MPC) problem, where the system's autonomous behavior is guided by the belief distribution. This approach enables continuous, gradual transitions across the full spectrum of autonomy levels, from direct teleoperation to full autonomy. To validate our approach, we conducted experiments to compare the performance of our proposed algorithm against two MPC-based shared autonomy methods. Compared to the baselines, our approach achieved reductions of at least 61% in object retrieval time, 44% in trajectory length, and 60% in human control input. Participants reported high perceived control, predictability, intent recognition, and responsiveness, along with low workload.