Max Robotics — Global Service Robot Directory + US Certification

About

Nils Dengler is a researcher at the forefront of autonomous robotics, specializing in active perception, robot navigation, and reinforcement learning. His work addresses critical challenges in enabling robots to operate intelligently in dynamic, cluttered, and human-populated environments. Dengler's major contributions include pioneering the NBV-SC framework for next-best view planning based on shape completion, a method that significantly improves fruit mapping and reconstruction for agricultural robotics by overcoming frequent occlusions. He has also advanced non-prehensile manipulation through deep reinforcement learning, enabling robots to push objects through cluttered scenes without prior knowledge of their dynamics. In human-aware navigation, Dengler developed novel approaches using long-term movement prediction and Bayesian inference to forecast human navigation goals, allowing service robots to move more safely and efficiently in indoor spaces. His work on handling sparse rewards in reinforcement learning using model predictive control addresses a fundamental bottleneck in training autonomous agents. With over 120 citations across his most-cited papers, Dengler's research has been published in top venues like IEEE Robotics and Automation Letters and IROS. His recent work on safe multi-agent reinforcement learning for cooperative navigation and manipulation-enhanced semantic mapping continues to push the boundaries of autonomous robot capabilities in real-world settings.