Balanced Information Gathering and Goal-Oriented Actions in Shared Autonomy

Robotic teleoperation can be a complex task due to factors such as high degree-of-freedom manipulators, operator inexperience, and limited operator situational awareness. To reduce teleoperation complexity, researchers have developed the shared autonomy control paradigm that involves joint control of a robot by a human user and an autonomous control system. We introduce the concept of active learning into shared autonomy by developing a method for systems to leverage information gathering: minimizing the system's uncertainty about user goals by moving to information-rich states to observe user input. We create a framework for balancing information gathering actions, which help the system gain information about user goals, with goal-oriented actions, which move the robot towards the goal the system has inferred from the user. We conduct an evaluation within the context of users who are multitasking that compares pure teleoperation with two forms of shared autonomy: our balanced system and a traditional goal-oriented system. Our results show significant improvements for both shared autonomy systems over pure teleoperation in terms of belief convergence about the user's goal and task completion speed and reveal trade-offs across shared autonomy strategies that may inform future investigations in this space.

• Publication year

  2019

• Venue

  IEEE/ACM International Conference on Human-Robot Interaction

• Publication date

  2019-03-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/HRI.2019.8673192
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Probabilistically Safe Robot Planning with Confidence-Based Human Predictions

  2018cited by this paper
• Planning for cars that coordinate with people: leveraging effects on human actions for planning and active information gathering over human internal state

  2018cited by this paper
• Goal-predictive robotic teleoperation from noisy sensors

  2017cited by this paper
• Opportunistic Active Learning for Grounding Natural Language Descriptions

  2017cited by this paper
• BIGnav: Bayesian Information Gain for Guiding Multiscale Navigation

  2017cited by this paper
• Shared autonomy via hindsight optimization for teleoperation and teaming

  2017cited by this paper
• Human-in-the-Loop Optimization of Shared Autonomy in Assistive Robotics

  2017cited by this paper
• Human-Robot Mutual Adaptation in Shared Autonomy

  2017cited by this paper
• Information gathering actions over human internal state

  2016cited by this paper
• Shared Autonomy via Hindsight Optimization

  2015influential reference
• A policy-blending formalism for shared control

  2013cited by this paper
• Formalizing Assistive Teleoperation

  2012cited by this paper
• Exploring Active Human Goal Inference in Shared Autonomy and Autonomous Driving

  2010cited by this paper
• Entropy-based active learning for object recognition

  2008cited by this paper
• Predicting Controller Capacity in Supervisory Control of Multiple UAVs

  2008cited by this paper
• Bayesian Inverse Reinforcement Learning

  2007cited by this paper
• Telemanipulation Assistance Based on Motion Intention Recognition

  2005cited by this paper
• Validating human-robot interaction schemes in multitasking environments

  2005cited by this paper
• Extracting User Intent in Mixed Initiative Teleoperator Control

  2004cited by this paper
• Human-Machine Collaborative Systems for Microsurgical Applications

  2003cited by this paper
• Seven principles of efficient human robot interaction

  2003cited by this paper
• Metrics for Evaluating Human-Robot Interactions

  2003cited by this paper
• Characterizing efficiency of human robot interaction: a case study of shared-control teleoperation

  2002cited by this paper
• Experiments in adjustable autonomy

  2001cited by this paper
• Cooperative Human and Machine Perception in Teleoperated Assembly

  2000cited by this paper
• Human integration into robot control utilising potential fields

  1997cited by this paper
• Learning Policies for Partially Observable Environments: Scaling Up

  1997cited by this paper

• A Unified Framework for Robots that Influence Humans over Long-Term Interaction

  2025cites this paper
• Toward Zero-Shot User Intent Recognition in Shared Autonomy

  2025cites this paper
• Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models

  2025cites this paper
• Shared Autonomy of a Robotic Manipulator for Grasping Under Human Intent Uncertainty Using POMDPs

  2024influential citation
• Active Inference-Based Planning for Safe Human-Robot Interaction: Concurrent Consideration of Human Characteristic and Rationality

  2024cites this paper
• Aligning Learning with Communication in Shared Autonomy

  2024cites this paper
• A Taxonomy of Robot Autonomy for Human-Robot Interaction

  2024cites this paper
• Integrated Data-driven Inference and Planning-based Human Motion Prediction for Safe Human-Robot Interaction

  2024cites this paper
• SARI: Shared Autonomy across Repeated Interaction

  2022cites this paper
• Learning to Share Autonomy from Repeated Human-Robot Interaction

  2022cites this paper
• Communicating Robot Conventions through Shared Autonomy

  2022cites this paper
• Non-Dyadic Interaction: A Literature Review of 15 Years of Human-Robot Interaction Conference Publications

  2022cites this paper
• Configuring Humans: What Roles Humans Play in HRI Research

  2022cites this paper
• Still Not Solved: A Call for Renewed Focus on User-Centered Teleoperation Interfaces

  2022cites this paper
• Enabling and Assessing Trust when Cooperating with Robots in Disaster Response (EASIER)

  2022cites this paper
• Information Theoretic Intent Disambiguation via Contextual Nudges for Assistive Shared Control

  2022cites this paper
• The Predictive Kinematic Control Tree: Enhancing Teleoperation of Redundant Robots through Probabilistic User Models

  2022cites this paper
• Connecting Human-Robot Interaction and Data Visualization

  2021cites this paper
• Toward Safe and Efficient Human–Robot Interaction via Behavior-Driven Danger Signaling

  2021cites this paper
• Active Altruism Learning and Information Sufficiency for Autonomous Driving

  2021cites this paper
• Learning to Share Autonomy Across Repeated Interaction

  2021cites this paper
• What Information Should a Robot Convey?

  2021cites this paper
• Perspective Taking for Shared Control

  2020cites this paper
• Benefits of Assistance over Reward Learning

  2020cites this paper
• Visualization of Intended Assistance for Acceptance of Shared Control

  2020cites this paper