Abstract
Human–Robot Interaction challenges Artificial Intelligence in many regards: dynamic, partially unknown environments that were not originally designed for robots; a broad variety of situations with rich semantics to understand and interpret; physical interactions with humans that requires fine, low-latency yet socially acceptable control strategies; natural and multi-modal communication which mandates common-sense knowledge and the representation of possibly divergent mental models. This article is an attempt to characterise these challenges and to exhibit a set of key decisional issues that need to be addressed for a cognitive robot to successfully share space and tasks with a human.We identify first the needed individual and collaborative cognitive skills: geometric reasoning and situation assessment based on perspective-taking and affordance analysis; acquisition and representation of knowledge models for multiple agents (humans and robots, with their specificities); situated, natural and multi-modal dialogue; human-aware task planning; human–robot joint task achievement. The article discusses each of these abilities, presents working implementations, and shows how they combine in a coherent and original deliberative architecture for human–robot interaction. Supported by experimental results, we eventually show how explicit knowledge management, both symbolic and geometric, proves to be instrumental to richer and more natural human–robot interactions by pushing for pervasive, human-level semantics within the robot's deliberative system.
Highlights
Human-Robot Interaction (HRI) represents a challenge for Artificial Intelligence (AI)
This article attempts to organise it into a coherent challenge for Artificial Intelligence, and to explain and illustrate some of the paths that we have investigated on our robots, that result in a set of deliberative, knowledge-oriented, software components designed for human-robot interaction
We first discuss how embodied cognition is an essential challenge in human-robot interaction; we rephrase the requirements of joint actions in terms of five questions; we discuss the importance of building and maintaining a multi-level model of the human; and we reflect on the importance of explicit knowledge management in robotic architectures that deal with human-level semantics and state in that respect the current limits of our logic framework
Summary
Human-Robot Interaction (HRI) represents a challenge for Artificial Intelligence (AI). The robot must be able to recognise, understand and participate in communication situations, both explicit (e.g. the human addresses verbally the robot) and implicit (e.g. the human points to an object); the robot must be able to take part in joint actions, both pro-actively (by planning and proposing resulting plans to the human) and reactively; the robot must be able to move and act in a safe, efficient and legible way, taking into account social rules like proxemics These three challenges, communication, joint action, human-aware execution, structure the research in humanrobot interaction.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have