Abstract
Automatic decision and lane-keeping tasks are the most fundamental but important tasks in robot controlling researches. Concerned about the computing limitations of mobile robot platforms, an easily trainable method with low computational consumption and low latency is needed to solve this problem. An unsupervised conditional reflex learning network was proposed in this paper, which uses the conditional pattern to learn the conditional pattern and make decisions in an unsupervised manner. We used the convolutional spiking neural network to extract hidden features of road lanes, and then used the dopamine modulation mechanism to learn the decision-making information from the acquired features. In order to evaluate the quality of automatic decision-making models, two metrics were designed which are total deviation distance per second (TDDPS) and target achievement rate during training (TAR). In the process of training, neither labels were given to the convolutional spiking neural network, nor artificial decision-making information was assigned to the dopamine modulation layer. Simulation experiments showed that the proposed model has a state-of-the-art performance in a relatively complicated scenario and solves three limitations mentioned in previous works. Our work brought more biological inspiration into decision support systems, with the hope that the proposed method can promote the development of the bionic decision support system in hardware, especially in neuromorphic hardware.
Highlights
Automatic decision and lane-keeping tasks are the most fundamental but important tasks in robot controlling researches
Wayve’s team made a car capable of autonomous driving ability in a single day [2], making reinforcement learning an important breakthrough in the Decision Support System (DSS)
Synaptic plasticity depends on the impulse activity of pre- and postsynaptic neurons, which corresponds to the spike-timing-dependent plasticity (STDP) synaptic learning algorithm widely used in Spiking neural network (SNN) [7], and on the regulation of neurohormones, such as acetylcholine [8], norepinephrine [9], serotonin [10] and dopamine [11]
Summary
Automatic decision and lane-keeping tasks are the most fundamental but important tasks in robot controlling researches. A decision model with biological plausibility works well in the on-board system of mobile robots Synaptic plasticity depends on the impulse activity of pre- and postsynaptic neurons, which corresponds to the spike-timing-dependent plasticity (STDP) synaptic learning algorithm widely used in SNN [7], and on the regulation of neurohormones, such as acetylcholine [8], norepinephrine [9], serotonin [10] and dopamine [11]. Inspired by the aforesaid neurobiology, a model named CR-SNN (Convolutional Reward-modulated Spiking Neural Network) consists of a feature-extraction unit and a decision-making unit was proposed in our work. The convolutional spiking neural network was applied to extract hidden features of road lanes, and the dopamine modulation mechanism was used to learn the decision-making information from the acquired features.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
