Justin Patton
Papers
6
Total Citations
173
H-Index
5
About
Justin Patton is a leading researcher at the intersection of robotics, RFID technology, and reinforcement learning, with a focus on automating complex, real-world inventory and navigation tasks. His most impactful contribution is the BFVP algorithm (109 citations), a probabilistic Bayesian filter that uses variable power RFID models to precisely localize passive UHF tags in challenging environments like warehouses and distribution centers. Patton also pioneered the use of mobile robots for autonomous retail inventory, demonstrating a novel system that significantly improves stock management efficiency (41 citations). His work extends to construction site automation, where he integrated RFID with Boston Dynamics’ SPOT robot to enable proactive tool tracking (9 citations). In reinforcement learning, Patton has advanced complete coverage path planning for robots navigating repeated obstacle environments (6 citations) and developed RIRL, a recurrent imitation and reinforcement learning method for long-horizon robotic tasks (5 citations). His multi-state-space reasoning approach further enhances robotic searching and planning in RFID-based systems (3 citations). Patton’s research is distinguished by its practical, industry-ready applications, bridging the gap between theoretical algorithms and deployable solutions in logistics, retail, and construction.
Research Focus
Key Achievements
Top Papers
- 1
- 2Mobile robot for retail inventory using RFID41 citations · 2016
- 3
- 4
- 5
- 6