2024 BrainChip Discussion, page-4274

Interesting research paper about the future directions for robotics:

“Neuromorphic Perception and Navigation for Mobile Robots: A Review

A. NOVO, University of Granada, Granada, Spain

F. LOBON, Instituto de Astrofísica de Andalucía (IAA-

CSIC), Granada, Spain H.G. DE MARINA, University of Granada, Granada, Spain

S. ROMERO, University of Granada, Granada, Spain

F. BARRANCO, University of Granada, Granada, Spain

With the fast and unstoppable evolution of robotics and artiicial intelligence, efective autonomous navigation in real-world scenarios has become one of the most pressing challenges in the literature. However, demanding requirements, such as real-time operation, energy and

computational eiciency, robustness, and reliability, make most current solutions unsuitable for real-world challenges. Thus, researchers are fostered to seek innovative approaches, such as bio-inspired solutions. Indeed, animals have the intrinsic ability to eiciently perceive, understand, and navigate their unstructured surroundings. To do so, they exploit self-motion cues, proprioception, and visual low in a cognitive process to map their environment and locate themselves within it. Computational neuroscientists

aim to answer łhow” and łwhy” such cognitive processes occur in the brain, to design novel neuromorphic sensors and methods that imitate biological processing. This survey aims to comprehensively review the application of brain-inspired strategies to autonomous navigation. Considering neuromorphic perception and asynchronous event processing, energy-eicient and adaptive learning, or the imitation of the working principles of brain areas that play a crucial role in navigation such as the hippocampus or the entorhinal cortex…”


“Finally, encouraging hardware development in the last years has made SNNs the focus of interest for the industry, with platforms such as Intel Loihi [Davies et al. 2018], IBM TrueNorth [Akopyan et al. 2015], or Brainchip Akida [Vanarse et al. 2019]”

https://dl.acm.org/doi/pdf/10.1145/3656469

It need not be said but Loihi is a research chip and TrueNorth has been sidelined. AKIDA is the only commercially available SNN with convolution.

My opinion only DYOR

Fact Finder