John Gonsalves
Papers
4
Total Citations
51
H-Index
4
About
John Gonsalves is a researcher at the forefront of Evolutionary Robotics (ER), specializing in the critical challenge of bridging the gap between simulation and reality. His work focuses on developing and comparing simulation techniques—from physics-based models to neural networks—for evolving robust robot controllers. Gonsalves’s most influential work, "A comparison of neural networks and physics models as motion simulators for simple robotic evolution" (20 citations), directly addresses the fundamental trade-offs in simulator fidelity for ER. He has systematically investigated these issues across multiple domains, including inverted pendulum control and, most notably, hexapod locomotion. His studies on hexapods, such as "Evolutionary Robotics Applied to Hexapod Locomotion" (12 citations), culminate in his key contribution: demonstrating the transferability of evolved controllers from simulation to real hardware. This work on hexapod locomotion transferability (4 citations) provides crucial empirical evidence for the viability of ER in real-world applications, making Gonsalves a significant voice in the ongoing effort to make evolved robots walk out of the computer and into the physical world.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4