Max Robotics — Global Service Robot Directory + US Certification

About

Bikramjit Banerjee is a researcher whose work spans robotics, machine learning, and multi-agent systems, with particular expertise in reinforcement learning, inverse reinforcement learning (IRL), and autonomous robot control. His most influential contribution, "Autonomous Acquisition of Behavior Trees for Robot Control" (2018, 50 citations), addresses a fundamental challenge in robotics: enabling intelligent agents to independently construct and refine behavior trees — control architectures widely used in both gaming and robotics — without human-designed scaffolding. This work represents a significant step toward truly autonomous robot decision-making. Banerjee has also made notable strides in inverse reinforcement learning, developing novel frameworks such as multi-task IRL approaches that account for experts demonstrating multiple interleaved strategies, and online IRL under occlusion, where learning must occur despite incomplete observational data. His work on adaptive multi-robot team reconfiguration using policy-reuse reinforcement learning further demonstrates his interest in scalable, flexible coordination among robot swarms. Collectively, his research addresses some of the most practically challenging problems in autonomous systems — how robots learn, adapt, and collaborate in complex, uncertain environments — making his contributions valuable reading for students and researchers working at the intersection of AI and robotics.