Desiderata for Planning Systems in General-Purpose Service Robots

Abstract

General-purpose service robots are expected to undertake a broad range of tasks at the request of users. Knowledge representation and planning systems are essential to flexible autonomous robots, but the field lacks a unified perspective on which features are essential for general-purpose service robots. Progress towards planning and reasoning for general-purpose service robots is hindered by differing assumptions about users, the environment, and the overall robot system. In this position paper, we propose desiderata for planning and reasoning systems to promote general-purpose service robots. Each proposed item draws on our experience with research on service robots in the office and home and on the demands of these environments. Our desiderata emphasize support for natural human-interfaces as well as for robust fallback methods when interactions with humans and the environment fail. We highlight relevant work towards these goals.

arXiv comment7th ICAPS Workshop on Planning and Robotics (PlanRob), 2019

References in corpus (6)

• The STRANDS Project: Long-Term Autonomy in Everyday Environments
• Explainable Planning
• Balancing Explicability and Explanation in Human-Aware Planning
• What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning
• Integrating Task-Motion Planning with Reinforcement Learning for Robust Decision Making in Mobile Robots
• Interaction and Autonomy in RoboCup@Home and Building-Wide Intelligence