Andrea Soltoggio
Loughborough University, University of Birmingham, Bielefeld University
Papers
12
Total Citations
296
H-Index
7
About
Andrea Soltoggio is a researcher whose work spans robotics, machine learning, and human-robot interaction, with particular expertise in neuroevolution, adaptive neural systems, and multi-robot coordination. His most-cited contribution, "Distributed Task Rescheduling With Time Constraints for the Optimization of Total Task Allocations in a Multirobot System" (2017, 146 citations), addresses a fundamental challenge in autonomous robotics: how to maximize task efficiency across distributed robot teams operating under real-world time pressures. This work has become an important reference in multi-robot systems research. Soltoggio has also made significant contributions to biologically inspired learning, exploring how neuromodulation and Hebbian plasticity can enable robots to learn from delayed and noisy rewards — problems that mirror the messy realities of natural environments. His work on human-robot interaction is equally notable, combining virtual reality methodologies to study worker well-being and adaptability alongside novel trust-recovery strategies following robotic accidents. More recently, he has pursued on-device deep reinforcement learning for resource-constrained autonomous systems. Collectively, his research bridges theoretical neuroscience-inspired learning with practical robotic applications, making him a distinctive voice at the intersection of adaptive intelligence and real-world robotics deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Evolvability of Neuromodulated Learning for Robots30 citations · 2008
- 4
- 5
- 6
- 7
- 8
- 9
- 10Real-time Hebbian Learning from Autoencoder Features for Control Tasks4 citations · 2014