Max Robotics — Global Service Robot Directory + US Certification

About

Devwrat Joshi is a roboticist whose research sits at the intersection of robotic manipulation, swarm intelligence, and learning for control. His work is notable for drawing inspiration from both classical physics and everyday human dexterity. Joshi’s most recognized contribution is the development of an analytical diabolo model, which enables robots to learn and perform the complex, dynamic task of playing a diabolo—a skill requiring precise coordination between two robotic arms. This work, published in 2021, has garnered 4 citations and bridges the gap between simulation and real-world execution. In parallel, Joshi has pioneered the application of the “Brazil nut effect”—a granular physics phenomenon—to robotic swarms, demonstrating how size-variable modules can self-segregate and migrate within a swarm without centralized control. This innovative approach, featured in multiple papers (2019, 2020), offers a scalable solution for reconfigurable robot collectives. He has also tackled the challenging problem of robotic contact juggling, where a robot must rapidly control a ball’s motion through indirect, intermittent contact. With a total of 14 citations across his top works, Joshi’s research is distinguished by its creative fusion of physical principles and machine learning, advancing both the theory and practice of dexterous, autonomous robotic systems.