Papers
11
Total Citations
131
H-Index
7
About
Peichen Wu is a roboticist whose research lies at the intersection of autonomous navigation, soft robotics, and intelligent manipulation. His most impactful work focuses on integrating deep reinforcement learning with map-based representations to enable mobile robots to navigate dynamic environments and avoid obstacles—a contribution that has garnered over 60 citations across related publications. Wu’s pioneering approach trains convolutional neural networks in simulation to predict steering actions directly from egocentric visual data, bridging the gap between virtual training and real-world deployment. He has also made significant strides in safe control for soft robotics, notably developing an IMU-based active safety system for variable stiffness soft actuators, which addresses a critical gap in ensuring robot safety under high-stress conditions. His recent work on compliant-based robotic 3D bin packing tackles the practical challenge of handling deformed cases and unavoidable uncertainties in industrial automation. Wu’s broader portfolio includes novel underactuated hand designs with multiple grasping modes and sensor-feedback-based soft grippers, demonstrating a commitment to creating versatile, robust robotic systems for unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Robot Navigation with Map-Based Deep Reinforcement Learning34 citations · 2020
- 2IMU-Based Active Safe Control of a Variable Stiffness Soft Actuator26 citations · 2019
- 3
- 4Compliant‐based robotic 3D bin packing with unavoidable uncertainties11 citations · 2023
- 5Reinforcement Learning for Robotic Safe Control with Force Sensing9 citations · 2019
- 6
- 7Robot Navigation with Map-Based Deep Reinforcement Learning8 citations · 2020
- 8
- 9An Automatic Grasp System with Sensor Feedback Based on Soft Gripper4 citations · 2018
- 10A New Grasping Mode Based on a Sucked-type Underactuated Hand3 citations · 2018