Papers
7
Total Citations
102
H-Index
5
About
Heiko Donat is a robotics researcher whose work sits at the intersection of surgical robotics and developmental artificial intelligence. His primary contributions lie in two distinct but equally challenging domains: force sensing and shape estimation for concentric tube continuum robots (CTCRs), and intrinsically motivated learning for developmental robots. In surgical robotics, Donat has pioneered data-driven methods to estimate tip contact forces and external forces along the backbone of CTCRs—among the smallest and most flexible instruments for minimally invasive surgery—using only a single force/torque sensor, enabling safe interaction without bulky integrated sensors. His real-time shape estimation algorithms, cited over 38 times, are critical for path planning and human-machine interaction in confined anatomical spaces. In developmental robotics, Donat tackles the high sample complexity of lifelong learning by proposing hierarchical, interest-driven exploration and goal babbling schemes that allow robots to autonomously bootstrap sensorimotor skills in open-ended environments. His work on spiking neural networks for anthropomorphic robot hands further demonstrates his commitment to bio-inspired, efficient control. With over 100 total citations and a publication record spanning 2020 to 2023, Donat is shaping the future of both safe surgical instruments and autonomous robot learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Efficient Online Interest-Driven Exploration for Developmental Robots9 citations · 2020
- 4
- 5
- 6
- 7