Adam Hines
Papers
3
Total Citations
19
H-Index
2
About
Adam Hines is a leading researcher at the intersection of neuromorphic computing and autonomous robotics, with a core focus on ultra-energy-efficient visual place recognition. His most impactful work, “A compact neuromorphic system for ultra–energy-efficient, on-device robot localization” (2025, 9 citations), demonstrates a transformative approach to deploying robotic navigation at the edge by overcoming the computational bottlenecks of traditional convolutional networks. Hines is also the architect of VPRTempo, a fast temporally encoded spiking neural network (SNN) for visual place recognition, detailed in two papers (2024, 8 citations; 2023, 2 citations). This work is pivotal in adapting SNNs—known for their low latency, energy efficiency, and continual learning capabilities—to real-world robotics tasks, a domain where they have seen limited application. Collectively, his contributions are shaping a new paradigm for on-device intelligence, enabling robots to localize with minimal power consumption. Hines’ research is essential reading for anyone interested in neuromorphic hardware, energy-efficient AI, or the future of autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3