Vision systems that enable collision avoidance, localization and navigation in complex and uncertain environments are common in biology, but are extremely challenging to mimic in artificial electronic systems, in part...Vision systems that enable collision avoidance, localization and navigation in complex and uncertain environments are common in biology, but are extremely challenging to mimic in artificial electronic systems, in particular when size and power limitations apply. The development of neuromorphic electronic systems implementing models of biological sensory-motor systems in silicon is one promising approach to addressing these challenges. Concept learning is a central part of animal cognition that enables appropriate motor response in novel situations by generalization of former experience, possibly from a few examples. These aspects make concept learning a challenging and important problem. Learning methods in computer vision are typically inspired by mammals, but recent studies of insects motivate an interesting complementary research direction. There are several remarkable results showing that honeybees can learn to master abstract concepts, providing a road map for future work to allow direct comparisons between bio-inspired computing architectures and information processing in miniaturized “real” brains. Considering that the brain of a bee has less than 0.01% as many neurons as a human brain, the task to infer a minimal architecture and mechanism of concept learning from studies of bees appears well motivated. The relatively low complexity of insect sensory-motor systems makes them an interesting model for the further development of bio-inspired computing architectures, in particular for resource-constrained applications such as miniature robots, wireless sensors and handheld or wearable devices. Work in that direction is a natural step towards understanding and making use of prototype circuits for concept learning, which eventually may also help us to understand the more complex learning circuits of the human brain. By adapting concept learning mechanisms to a polymorphic computing framework we could possibly create large-scale decentralized computer vision systems, for example in the form of wireless sensor networks.展开更多
Tactile perception in artificial systems remains constrained by the von Neumann architecture,where the separation ofmemory and computation leads to significant latency and energy inefficiency.Neuromorphic engineering ...Tactile perception in artificial systems remains constrained by the von Neumann architecture,where the separation ofmemory and computation leads to significant latency and energy inefficiency.Neuromorphic engineering provides abiologically inspired alternative by adopting event-driven,spike-based coding,akin to neural signaling in humansomatosensory systems.This review systematically examines spike-based neural coding techniques for tactileperception,focusing on three key aspects:encoding strategies,neuromorphic hardware implementations,anddecoding methodologies.It compares rate coding and temporal coding in terms of biological plausibility andcomputational efficiency,particularly in dynamic and high-speed tactile tasks.A range of hardware platforms isevaluated,including oscillator-based encoding circuits,CMOS and memristor-based spiking neurons,and self-poweredtactile sensors using triboelectric nanogenerators.On the decoding side,mechanisms such as spike-timing-dependentplasticity and spiking neural networks are analyzed for their potential to support adaptive,online learning in tactilesystems.The review emphasizes co-design approaches that integrate sensing,encoding,and processing within aunified framework to achieve system-level efficiency.By bridging advances in functional materials,low-powerhardware,and brain-inspired computation,this work outlines a roadmap toward artificial tactile systems withmillisecond-level latency,sub-milliwatt power consumption,and high perceptual fidelity.These capabilities areessential for future applications in robotics,prosthetics,and wearable electronics.展开更多
基金partially supported by the Swedish Foundation for International Cooperation in Research and Higher Education(STINT),grant number IG2011-2025ARC DP0878968/DP0987989 for funding support.
文摘Vision systems that enable collision avoidance, localization and navigation in complex and uncertain environments are common in biology, but are extremely challenging to mimic in artificial electronic systems, in particular when size and power limitations apply. The development of neuromorphic electronic systems implementing models of biological sensory-motor systems in silicon is one promising approach to addressing these challenges. Concept learning is a central part of animal cognition that enables appropriate motor response in novel situations by generalization of former experience, possibly from a few examples. These aspects make concept learning a challenging and important problem. Learning methods in computer vision are typically inspired by mammals, but recent studies of insects motivate an interesting complementary research direction. There are several remarkable results showing that honeybees can learn to master abstract concepts, providing a road map for future work to allow direct comparisons between bio-inspired computing architectures and information processing in miniaturized “real” brains. Considering that the brain of a bee has less than 0.01% as many neurons as a human brain, the task to infer a minimal architecture and mechanism of concept learning from studies of bees appears well motivated. The relatively low complexity of insect sensory-motor systems makes them an interesting model for the further development of bio-inspired computing architectures, in particular for resource-constrained applications such as miniature robots, wireless sensors and handheld or wearable devices. Work in that direction is a natural step towards understanding and making use of prototype circuits for concept learning, which eventually may also help us to understand the more complex learning circuits of the human brain. By adapting concept learning mechanisms to a polymorphic computing framework we could possibly create large-scale decentralized computer vision systems, for example in the form of wireless sensor networks.
基金supported by the Stable Support Plan Program of Shenzhen Natural Science Fund[grant number 20231120204356001]the Guangdong Basic and Applied Basic Research Foundation[grant number 2024A1515030156]the funding from Tencent Robotics X.
文摘Tactile perception in artificial systems remains constrained by the von Neumann architecture,where the separation ofmemory and computation leads to significant latency and energy inefficiency.Neuromorphic engineering provides abiologically inspired alternative by adopting event-driven,spike-based coding,akin to neural signaling in humansomatosensory systems.This review systematically examines spike-based neural coding techniques for tactileperception,focusing on three key aspects:encoding strategies,neuromorphic hardware implementations,anddecoding methodologies.It compares rate coding and temporal coding in terms of biological plausibility andcomputational efficiency,particularly in dynamic and high-speed tactile tasks.A range of hardware platforms isevaluated,including oscillator-based encoding circuits,CMOS and memristor-based spiking neurons,and self-poweredtactile sensors using triboelectric nanogenerators.On the decoding side,mechanisms such as spike-timing-dependentplasticity and spiking neural networks are analyzed for their potential to support adaptive,online learning in tactilesystems.The review emphasizes co-design approaches that integrate sensing,encoding,and processing within aunified framework to achieve system-level efficiency.By bridging advances in functional materials,low-powerhardware,and brain-inspired computation,this work outlines a roadmap toward artificial tactile systems withmillisecond-level latency,sub-milliwatt power consumption,and high perceptual fidelity.These capabilities areessential for future applications in robotics,prosthetics,and wearable electronics.
