جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

2 مُخرَج نتائج البحث عن «collision avoidance»

مقالوصول مفتوح202518استشهاد· Semantic Scholar

Novel deep reinforcement learning based collision avoidance approach for path planning of robots in unknown environment

PLoS ONE · مجلد 20 (1) · e0312559-e0312559

Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system's capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach's agent converged in 210th episodes in a cluttered environment and 400th episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.

collision avoidancerobot path planningdeep reinforcement learningQ-learning
مقالوصول مغلق2025

Trajectory Planning-Based Reinforcement Learning for 3-D Indoor Navigation of Autonomous Aerial Vehicle

IEEE Communications Standards Magazine · 1-8

The development of indoor navigation and positioning technology autonomous aerial vehicles, or AAVs, are employed extensively in many different industries due to their ease of operation and outstanding mobility. Drones can decrease responder injuries, increase mission effectiveness, and conduct search operations in locations that rescue crews are unable to access when utilized for indoor search and rescue during a disaster. This paper’s goal is to use a reinforcement learning algorithm to suggest a track planning technique for AAVs in indoor post-disaster scenarios. The difficulty of finding a safe path for AAVs in crowded indoor areas that present a significant risk to flight safety is the focus of this research. To address the difficulties caused by the intricate interior environment and the sluggish convergence of current reinforcement learning algorithms, an ensemble strategy based on reinforcement learning has been put forth. By using the coordinate connection between the beginning point and the endpoint to identify the primary barrier and the nodes surrounding it, this strategy seeks to minimize the search for superfluous nodes. The enhanced 3D navigation trajectory planning technique lowered the number of space search nodes by 55.49% and shortened the convergence time by 98.57%, according to simulation and testing of the optimization process in a three-dimensional grid diagram.

trajectory planningreinforcement learningautonomous aerial vehiclesindoor navigation