Max Robotics — Global Service Robot Directory + US Certification

About

Pengzhan Chen is a leading researcher at the intersection of robotics, artificial intelligence, and autonomous systems, with a primary focus on enabling intelligent robots to perceive, navigate, and manipulate objects in complex, dynamic environments. His most impactful work, "Deep reinforcement learning based moving object grasping" (64 citations), pioneers the use of deep reinforcement learning for real-time robotic grasping of moving targets, a critical capability for industrial automation and service robotics. Chen further advances mobile robot navigation with his SAC-LSTM algorithm (24 citations), which integrates long short-term memory networks with reinforcement learning to achieve faster, more adaptive path planning in cluttered indoor spaces. His contributions to visual perception are equally notable: the TSG-SLAM system (9 citations) tightly couples instance segmentation with geometric constraints to maintain robust localization and mapping even amidst moving objects, while his adaptive UKF-based fusion method (8 citations) enhances monocular and binocular ranging accuracy under uncertainty. More recently, Chen has addressed the challenge of autonomous grasping in cluttered scenes (3 citations), developing strategies for multi-class object manipulation. With over 100 total citations and a growing portfolio of high-impact publications, Chen is establishing himself as a key innovator in creating perceptive, reactive, and dexterous robotic systems for real-world applications.