Volker Gabler
Papers
12
Total Citations
188
H-Index
8
About
Volker Gabler is a robotics and artificial intelligence researcher whose work spans three interconnected domains: multi-agent reinforcement learning, human-robot collaboration, and robot motion planning. His research has made notable contributions to advancing autonomous systems that operate safely and efficiently alongside humans in real-world environments. In multi-agent reinforcement learning, Gabler's 2019 paper on reducing overestimation bias using double centralized critics stands as his most influential work, accumulating 70 citations and addressing a fundamental weakness in cooperative learning systems. His 2024 work on decentralized best-response policies continues this thread, demonstrating sustained commitment to scalable multi-agent architectures. Gabler has also shaped the field of human-robot collaboration, developing game-theoretic frameworks for adaptive action selection, human motion prediction for obstacle avoidance, and legible robot behavior — research particularly relevant to industrial assembly environments where safety and fluid cooperation are paramount. His later contributions tackle the practical challenges of deploying robots on industrial platforms, including force-sensitive grasping under uncertainty and probabilistic motion planning via Gaussian Belief Propagation. With over 180 cumulative citations, Gabler's body of work bridges theoretical machine learning with pragmatic robotics engineering, making him a valuable reference for researchers working at the intersection of autonomous systems and human-centered design.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8Legible action selection in human-robot collaboration8 citations · 2017
- 9
- 10MS2MP: A Min-Sum Message Passing Algorithm for Motion Planning3 citations · 2021