BANSAI: Towards Bridging the AI Adoption Gap in Industrial Robotics with Neurosymbolic Programming
This addresses the problem of slow AI adoption in industrial robotics for practitioners, though it appears incremental by unifying prior research.
The paper tackles the gap between deep learning advances and traditional programming in industrial robotics by proposing BANSAI, a neurosymbolic AI approach that enables data-driven program synthesis and optimization, aiming for practical validation in real-world workflows.
Over the past decade, deep learning helped solve manipulation problems across all domains of robotics. At the same time, industrial robots continue to be programmed overwhelmingly using traditional program representations and interfaces. This paper undertakes an analysis of this "AI adoption gap" from an industry practitioner's perspective. In response, we propose the BANSAI approach (Bridging the AI Adoption Gap via Neurosymbolic AI). It systematically leverages principles of neurosymbolic AI to establish data-driven, subsymbolic program synthesis and optimization in modern industrial robot programming workflow. BANSAI conceptually unites several lines of prior research and proposes a path toward practical, real-world validation.