Papers
8
Total Citations
136
H-Index
5
About
Alpha Renner is pioneering the intersection of neuromorphic computing and robotics, with a core focus on developing spiking neural networks (SNNs) that enable energy-efficient, biologically-inspired perception and navigation. Their major contributions lie in translating theoretical models of path integration, map formation, and pose estimation into working systems on neuromorphic hardware, most notably Intel’s Loihi chip. Renner’s landmark work, “Pose Estimation and Map Formation with Spiking Neural Networks: towards Neuromorphic SLAM” (53 citations), established a foundational architecture for neuromorphic simultaneous localization and mapping (SLAM), demonstrating how ultra low-power analog/digital circuits can perform complex spatial reasoning. This was followed by a fully on-chip implementation for head pose estimation on the iCub humanoid robot (28 citations), proving the practical viability of neuromorphic control. More recently, Renner has advanced visual scene understanding using resonator networks, achieving robust visual odometry and scene decomposition with minimal energy cost. Their work on error estimation and correction in SNNs for map formation (21 citations) addresses a critical challenge in deploying neuromorphic systems in real-world robots. By consistently demonstrating that neuromorphic hardware can match or exceed traditional algorithms in efficiency, Renner is a leading voice in the push toward truly autonomous, low-power robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Neuromorphic visual scene understanding with resonator networks17 citations · 2024
- 5Visual odometry with neuromorphic resonator networks10 citations · 2024
- 6Neuromorphic Visual Scene Understanding with Resonator Networks3 citations · 2022
- 7Self-calibration and learning on chip: towards neuromorphic robots2 citations · 2019
- 8Visual Odometry with Neuromorphic Resonator Networks2 citations · 2022