Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Maximum Solar Energy Tracking Leverage High-DoF Robotics System with Deep Reinforcement Learning

Anjie Jiang, Kangtong Mo, Satoshi Fujimoto, Michael Taylor, Sanjay Kumar, Chiotis Dimitrios, Emilia Ruiz

TL;DR

This work introduces an innovative objectness regularization framework that compels tracking points to remain confined within the delineated boundaries of the solar entity, and leverages the high-DoF robot arm to integrate the method to improve its robustness and flexibility in different outdoor environments.

Abstract

Solar trajectory monitoring is a pivotal challenge in solar energy systems, underpinning applications such as autonomous energy harvesting and environmental sensing. A prevalent failure mode in sustained solar tracking arises when the predictive algorithm erroneously diverges from the solar locus, erroneously anchoring to extraneous celestial or terrestrial features. This phenomenon is attributable to an inadequate assimilation of solar-specific objectness attributes within the tracking paradigm. To mitigate this deficiency inherent in extant methodologies, we introduce an innovative objectness regularization framework that compels tracking points to remain confined within the delineated boundaries of the solar entity. By encapsulating solar objectness indicators during the training phase, our approach obviates the necessity for explicit solar mask computation during operational deployment. Furthermore, we leverage the high-DoF robot arm to integrate our method to improve its robustness and flexibility in different outdoor environments.

Maximum Solar Energy Tracking Leverage High-DoF Robotics System with Deep Reinforcement Learning

TL;DR

This work introduces an innovative objectness regularization framework that compels tracking points to remain confined within the delineated boundaries of the solar entity, and leverages the high-DoF robot arm to integrate the method to improve its robustness and flexibility in different outdoor environments.

Abstract

Solar trajectory monitoring is a pivotal challenge in solar energy systems, underpinning applications such as autonomous energy harvesting and environmental sensing. A prevalent failure mode in sustained solar tracking arises when the predictive algorithm erroneously diverges from the solar locus, erroneously anchoring to extraneous celestial or terrestrial features. This phenomenon is attributable to an inadequate assimilation of solar-specific objectness attributes within the tracking paradigm. To mitigate this deficiency inherent in extant methodologies, we introduce an innovative objectness regularization framework that compels tracking points to remain confined within the delineated boundaries of the solar entity. By encapsulating solar objectness indicators during the training phase, our approach obviates the necessity for explicit solar mask computation during operational deployment. Furthermore, we leverage the high-DoF robot arm to integrate our method to improve its robustness and flexibility in different outdoor environments.

Paper Structure

This paper contains 8 sections, 6 equations, 5 figures.

Table of Contents

  1. Introduction
  2. Related works
  3. Methodology
  4. Preliminary
  5. Object Detection Algorithm
  6. Deep-Q Neural Network
  7. Experiment Results
  8. Conclusion

Figures (5)

  • Figure 1: Smart Solar energy collection system using High-DoF robotics with.
  • Figure 2: Experimental testbed setup. Using a mini-robot arm(6 DoF) with a solar panel to collect solar energy in the outdoor environment in Melbourne.
  • Figure 3: Graph showing the performance on success rate for tasks used in agent training, illustrating the effectiveness of the training process.
  • Figure 4: Performance (success rate) on tasks that are used for agent training
  • Figure 5: Performance in solar energy collection.