Neuromorphic engineering aims to apply insights from neurobiological knowledge to develop next-generation artificial intelligence for computation, sensing, and control of robotic systems. There has been a rapid development of neuromorphic engineering technologies for robotics due to several developments. Firstly, the success and limitation of deep neural networks greatly inspire the research potential that biological intelligence can further boost the computing performance of artificial intelligence in terms of data, power, and computing efficiency. Second, the emergence of novel neuromorphic hardware and sensors has shown greater application-level performance compared with conventional CPU and GPU. Third, the pace of progress in neuroscience has accelerated dramatically in recent years, providing a wealth of new understanding and insights about the functioning of brains at the neuron level.
Neuromorphic engineering therefore can represent a fundamental revolution for robotics in many ways. This Research Topic seeks to invite theoretical and experimental results dealing with neuromorphic engineering technologies for the design, control, and real-world applications of robotic systems. Specifically, this Research Topic investigates interdisciplinary innovation in many areas of robots, such as environmental sensing, novel computational models and architectures, hybrid simulation of physics and brain-inspired networks, and artificial intelligence and machine learning. We welcome research articles, reviews, datasets, or benchmarks tested in real-world applications.
Topics of interest include, but are not limited to:
• Theoretical research focused on neuromorphic technology deployment, including formal verification, novel frameworks, and neuroscience basis for robotics-related tasks.
• Algorithms that leverage the novel features of neuromorphic computing, which include novel computation models, optimization methods, and learning paradigms for robotic tasks.
• Robotic system applications or demonstrators that demonstrate a neuromorphic approach is uniquely capable of outperforming state-of-the-art solutions.
• Simulation frameworks or technologies for neurorobotics, such as demonstrator, sim-2-real transfer, or parallel computing.
• Benchmarking and datasets on neuromorphic hardware or sensors in real-world scenarios.
Neuromorphic engineering aims to apply insights from neurobiological knowledge to develop next-generation artificial intelligence for computation, sensing, and control of robotic systems. There has been a rapid development of neuromorphic engineering technologies for robotics due to several developments. Firstly, the success and limitation of deep neural networks greatly inspire the research potential that biological intelligence can further boost the computing performance of artificial intelligence in terms of data, power, and computing efficiency. Second, the emergence of novel neuromorphic hardware and sensors has shown greater application-level performance compared with conventional CPU and GPU. Third, the pace of progress in neuroscience has accelerated dramatically in recent years, providing a wealth of new understanding and insights about the functioning of brains at the neuron level.
Neuromorphic engineering therefore can represent a fundamental revolution for robotics in many ways. This Research Topic seeks to invite theoretical and experimental results dealing with neuromorphic engineering technologies for the design, control, and real-world applications of robotic systems. Specifically, this Research Topic investigates interdisciplinary innovation in many areas of robots, such as environmental sensing, novel computational models and architectures, hybrid simulation of physics and brain-inspired networks, and artificial intelligence and machine learning. We welcome research articles, reviews, datasets, or benchmarks tested in real-world applications.
Topics of interest include, but are not limited to:
• Theoretical research focused on neuromorphic technology deployment, including formal verification, novel frameworks, and neuroscience basis for robotics-related tasks.
• Algorithms that leverage the novel features of neuromorphic computing, which include novel computation models, optimization methods, and learning paradigms for robotic tasks.
• Robotic system applications or demonstrators that demonstrate a neuromorphic approach is uniquely capable of outperforming state-of-the-art solutions.
• Simulation frameworks or technologies for neurorobotics, such as demonstrator, sim-2-real transfer, or parallel computing.
• Benchmarking and datasets on neuromorphic hardware or sensors in real-world scenarios.
