Optimizing Reinforcement Learning-Based Visual Navigation for Resource-Constrained Devices

Optimizing Reinforcement Learning-Based Visual Navigation for Resource-Constrained Devices

Existing work on Deep reinforcement learning-based visual navigation mainly focuses on autonomous agents with ample power and compute resources. However, Reinforcement learning for visual navigation on resource-constrained devices remains an under-explored area of research, primarily due to challeng...

Full description

Bibliographic Details
Main Authors: U. Vijetha, V. Geetha
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Collision detection and avoidance
reinforcement learning (RL)
resource-constrained settings
reward shaping
Sim2Real transferability
state abstraction
Online Access:https://ieeexplore.ieee.org/document/10278417/

Internet

https://ieeexplore.ieee.org/document/10278417/

Similar Items