Jeroen Burms
Papers
2
Total Citations
14
H-Index
2
About
Jeroen Burms explores the frontiers of embodied intelligence and compliant robotics, where the physical body itself becomes part of the control system. His research centers on how morphological computation—offloading control complexity to body dynamics—can simplify learning and adaptation in robots. In his most cited work, "Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics" (2015, 12 citations), Burms demonstrates that a simple, biologically inspired learning rule can effectively train systems that leverage their own physical compliance, extending Hebbian plasticity beyond traditional neural network paradigms. This work offers a compelling bridge between neuroscience and robotics, showing how reward signals can guide learning in embodied systems. Burms also contributes to autonomous terrain recognition, as seen in "Online Unsupervised Terrain Classification for a Compliant Tensegrity Robot Using a Mixture of Echo State Networks" (2015, 2 citations), where he develops an online learning algorithm that enables a tensegrity robot to segment its sensorimotor stream and classify its environment without supervision. Though early in his career, Burms’ work is foundational for researchers seeking to build robots that learn through interaction with the physical world, rather than relying solely on pre-programmed models.
Research Focus
Key Achievements
Top Papers
- 1
- 2