Max Robotics — Global Service Robot Directory + US Certification

About

Jiale Dong is a robotics researcher focused on advancing human-robot skill transfer, particularly for contact-rich manipulation tasks in dynamic environments. Their work centers on enabling robots to learn, generalize, and adapt complex physical skills from human demonstrations, with a strong emphasis on handling curved surfaces and variable stiffness. Dong’s most cited paper (2023, 23 citations) introduces a novel framework that combines learning from demonstration with adaptive control, significantly improving a robot’s ability to complete multi-step contact tasks in unknown settings—a critical step toward more dexterous and autonomous manufacturing and service robots. Their earlier contributions include a modified Dynamic Movement Primitive (DMP) method for generalizing skills on curved surfaces (2022, 8 citations) and an online adaptive stiffness adjustment technique (2021, 4 citations) that allows robots to modulate compliance in real time. Most recently, Dong has tackled the challenge of learning from multiple demonstrations using a generalized Gaussian mixture model (2023, 3 citations), overcoming the limitations of single-demonstration approaches. With a growing citation record and a clear trajectory toward practical, adaptable robotic manipulation, Dong is establishing a reputation for bridging theoretical learning models with real-world physical interaction.