arXiv subjects

Mir Feroskhan

Publications and source records attributed to Mir Feroskhan.

21 records · Page 2Linked to original sources

arXiv2024

Vision-based Learning for Drones: A Survey

Drones as advanced cyber-physical systems are undergoing a transformative shift with the advent of vision-based learning, a field that is rapidly gaining prominence due to its profound impact on drone autonomy and functionality. Different from existing task-specific surveys, this review offers a comprehensive overview of vision-based learning in drones, emphasizing its pivotal role in enhancing their operational capabilities under various scenarios. We start by elucidating the fundamental principles of vision-based learning, highlighting how it significantly improves drones' visual perception and decision-making processes. We then categorize vision-based control methods into indirect, semi-direct, and end-to-end approaches from the perception-control perspective. We further explore various applications of vision-based drones with learning capabilities, ranging from single-agent systems to more complex multi-agent and heterogeneous system scenarios, and underscore the challenges and innovations characterizing each area. Finally, we explore open questions and potential solutions, paving the way for ongoing research and development in this dynamic and rapidly evolving field. With growing large language models (LLMs) and embodied intelligence, vision-based learning for drones provides a promising but challenging road towards artificial general intelligence (AGI) in 3D physical world.

cs.RO↗

arXiv2023

Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approach

Equipping drones with target search capabilities is highly desirable for applications in disaster rescue and smart warehouse delivery systems. Multiple intelligent drones that can collaborate with each other and maneuver among obstacles show more effectiveness in accomplishing tasks in a shorter amount of time. However, carrying out collaborative target search (CTS) without prior target information is extremely challenging, especially with a visual drone swarm. In this work, we propose a novel data-efficient deep reinforcement learning (DRL) approach called adaptive curriculum embedded multistage learning (ACEMSL) to address these challenges, mainly 3-D sparse reward space exploration with limited visual perception and collaborative behavior requirements. Specifically, we decompose the CTS task into several subtasks including individual obstacle avoidance, target search, and inter-agent collaboration, and progressively train the agents with multistage learning. Meanwhile, an adaptive embedded curriculum (AEC) is designed, where the task difficulty level (TDL) can be adaptively adjusted based on the success rate (SR) achieved in training. ACEMSL allows data-efficient training and individual-team reward allocation for the visual drone swarm. Furthermore, we deploy the trained model over a real visual drone swarm and perform CTS operations without fine-tuning. Extensive simulations and real-world flight tests validate the effectiveness and generalizability of ACEMSL. The project is available at https://github.com/NTU-UAVG/CTS-visual-drone-swarm.git.

cs.RO↗

arXiv2020

Bio-Inspired Synergistic Wing and Tail Morphing Extends Flight Capabilities of Drones

The operation of drones in cluttered environments and over extended areas demands adaptive flight capabilities to meet the opposing aerodynamic requirements of agile and fast cruise flight. High agility and maneuverability are required to aggressively navigate around obstacles and to perform instantaneous takeoffs or landings, while high energy efficiency is desired when covering large distances. In nature, these requirements are met by some birds by synergistic adaptation of wings and tail, such as the northern goshawk, which displays high agility and maneuverability when flying through forests and fast steady flight capabilities when ambushing prey in the open field. In this article, we experimentally study the effects of bio-inspired wing and tail morphing on flight performance by means of a novel morphing drone. We show that the combined morphing of wing and tail can improve agility, maneuverability, stability, flight velocity range, and energy efficiency of a winged drone. The drone's flight performance is validated in wind tunnel tests, shape optimization studies and outdoor flight tests.

physics.flu-dyn↗