Designing Robot Behavior in Human-Robot Interactions

In this book, we have set up a unified analytical framework for various human-robot systems, which involve peer-peer interactions (either space-sharing or time-sharing) or hierarchical interactions. A methodology in designing the robot behavior through control, planning, decision and learning is proposed. In particular, the following topics are discussed in-depth: safety during human-robot interactions, efficiency in real-time robot motion planning, imitation of human behaviors from demonstration, dexterity of robots to adapt to different environments and tasks, cooperation among robots and humans with conflict resolution. These methods are applied in various scenarios, such as human-robot collaborative assembly, robot skill learning from human demonstration, interaction between autonomous and human-driven vehicles, etc. Key Features: Proposes a unified framework to model and analyze human-robot interactions under different modes of interactions. Systematically discusses the control, decision and learning algorithms to enable robots to interact safely with humans in a variety of applications. Presents numerous experimental studies with both industrial collaborative robot arms and autonomous vehicles.

Table of Contents SECTION I INTRODUCTIONIntroduction Human-Robot Interactions: An OverviewModes of Interactions Robot Behavior System Design Objectives System Evaluation Outline of the Book FrameworkMulti-Agent Framework Agent Behavior Design and ArchitectureConclusion SECTION II THEORY Safety during Human-Robot InteractionsOverviewSafety-Oriented Behavior DesignSafe Set Algorithm Safe Exploration AlgorithmAn Integrated Method for Safe Motion Control Conclusion Efficiency in Real-Time Motion PlanningOverviewProblem Formulation Optimization-Based Trajectory Planning Optimization-Based Speed Profile Planning Optimization-Based Layered PlanningConclusion Imitation: Mimicking Human Behavior OverviewImitation for PredictionImitation for Action Conclusion Dexterity: Analogy Learning to Expand Robot Skill Sets OverviewConcept of Analogy Learning Advantages of Analogy Learning Structure Preserved Registration for Analogy LearningExperimental Study Conclusion Cooperation: Conflict Resolution during InteractionsOverviewDynamics of Multi-Agent Systems Cooperation under Information Asymmetry Conflict Resolution through CommunicationConclusion SECTION III APPLICATIONS Human-Robot Co-existence: Space-Sharing InteractionsOverviewRobot Safe Interaction System for Industrial RobotsRobustly-Safe Automated Driving SystemConclusion Robot Learning from Human: Hierarchical InteractionsOverviewRemote Lead Through Teaching for Implementing Imitation LearningRobotic Grasping by Analogy LearningRobotic Motion Re-planning by Analogy LearningConclusion Human-Robot Collaboration: Time-Sharing Interactions Human-Robot Collaboration in ManufacturingSafe and Efficient Robot Collaborative SystemExperimental Study Conclusion SECTION IV CONCLUSION Vision for Future Robotics and Human-Robot InteractionsRoadmap to the FutureConclusion of the Book References Index

Changliu Liu is an assistant professor in the Robotics Institute at Carnegie Mellon University, where she leads the Intelligent Control Lab. She received her PhD degree from University of California at Berkeley in 2017. Her research interests include: robotics and human-robot interactions, control and motion planning, optimization and optimal control, multi-agent system and game theory, design and verification of safe intelligent systems. Te Tang received his PhD degree from University of California at Berkeley in 2018. He joined FANUC America Corporation in 2018, and he is currently a researcher at FANUC Advanced Research Laboratory. His research interests include robotics, learning from demonstration, computer vision and their industrial applications. Hsien-Chung Lin is a research engineer in FANUC Advanced Research Laboratory at FANUC America Corporation. Prior to joining FANUC, he received his Ph.D. degree from University of California at Berkeley in 2018. His research interests cover robotics, optimal control, human-robot interaction, learning from demonstration and motion planning. Masayoshi Tomizuka received his PhD degree from MIT in 1974. In 1974, he joined the Mechanical Engineering Department of the University of California, Berkeley, where he currently is Cheryl and John Neerhout, Jr., Distinguished Professor. His research interests are control theory and its applications to mechatronic systems such as robots. He is a Life Fellow of ASME and IEEE, and a Fellow of IFAC. He was awarded the Rufus Oldenburger Medal (2002) and the Richard Bellman Control Heritage Award (2018).