English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Traditional visual navigation methods of micro aerial vehicle (MAV) usuallycalculate a passable path that satisfies the constraints depending on a priormap. However, these methods have issues such as high demand for computingresources and poor robustness in face of unfamiliar environments. Aiming tosolve the above problems, we propose a neuromorphic reinforcement learningmethod (Neuro-Planner) that combines spiking neural network (SNN) and deepreinforcement learning (DRL) to realize MAV 3D visual navigation with depthcamera. Specifically, we design spiking actor network based on two-state LIF(TS-LIF) neurons and its encoding-decoding schemes for efficient inference.Then our improved hybrid deep deterministic policy gradient (HDDPG) andTS-LIF-based spatio-temporal back propagation (STBP) algorithms are used as thetraining framework for actor-critic network architecture. To verify theeffectiveness of the proposed Neuro-Planner, we carry out detailed comparisonexperiments with various SNN training algorithm (STBP, BPTT and SLAYER) in thesoftware-in-the-loop (SITL) simulation framework. The navigation success rateof our HDDPG-STBP is 4.3\% and 5.3\% higher than that of the original DDPG inthe two evaluation environments. To the best of our knowledge, this is thefirst work combining neuromorphic computing and deep reinforcement learning forMAV 3D visual navigation task.

Neuro-Planner: A 3D Visual Navigation Method for MAV with Depth Camera based on Neuromorphic Reinforcement Learning