A Path Planning Algorithm for Smooth Trajectories of Unmanned Aerial Vehicles via Potential Fields

Huang, Shuangyao; Low, Kin Huat

doi:10.1109/icarcv.2018.8581198

Cited by 7 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intensive research has been conducted on collision avoidance for UAV swarms. Conventional methods include Velocity Obstacles (VO) [9], Artificial Potential Field (APF) [10], Particle Swarm Optimization (PSO) [11] and hybrid methods [3]. VO based methods require reliable communications among UAVs.…”

Section: A Collision Avoidance For Uav Swarmsmentioning

confidence: 99%

Multi-UAV Collision Avoidance using Multi-Agent Reinforcement Learning with Counterfactual Credit Assignment

Huang¹,

Zhang²,

Huang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-UAV collision avoidance is a challenging task for UAV swarm applications due to the need of tight cooperation among swarm members for collision-free path planning. Centralized Training with Decentralized Execution (CTDE) in Multi-Agent Reinforcement Learning is a promising method for multi-UAV collision avoidance, in which the key challenge is to effectively learn decentralized policies that can maximize a global reward cooperatively. We propose a new multi-agent critic-actor learning scheme called MACA for UAV swarm collision avoidance. MACA uses a centralized critic to maximize the discounted global reward that considers both safety and energy efficiency, and an actor per UAV to find decentralized policies to avoid collisions. To solve the credit assignment problem in CTDE, we design a counterfactual baseline that marginalizes both an agent's state and action, enabling to evaluate the importance of an agent in the joint observation-action space. To train and evaluate MACA, we design our own simulation environment MACAEnv to closely mimic the realistic behaviors of a UAV swarm. Simulation results show that MACA achieves more than 16% higher average reward than two state-of-the-art MARL algorithms and reduces failure rate by 90% and response time by over 99% compared to a conventional UAV swarm collision avoidance algorithm in all test scenarios.

show abstract

Section: A Collision Avoidance For Uav Swarmsmentioning

confidence: 99%

Multi-UAV Collision Avoidance using Multi-Agent Reinforcement Learning with Counterfactual Credit Assignment

Huang¹,

Zhang²,

Huang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another popular method for ODA is Artificial Potential Field (APF). For example, a method combining an attractive field and a repulsive field is developed to generate safe and smooth trajectories for UAVs in urban environments (Huang and Low 2018). Though this method is more energy efficient than VO, it didn't address the coordination of a swarm of robots in ODA, which may result in collisions between robots themselves in a swarm.…”

Section: Related Workmentioning

confidence: 99%

“…ODA is a long-standing problem in robotics. With the ever increasing number of applications of UAVs in recent years, extensive studies have been conducted on ODA for UAVs, including Velocity Obstacles (Liu et al 2018;Snape et al 2011), Artificial Potential Fields (Huang and Low 2018;Tsang et al 2018), and hybrid methods combining more than one approach (Pradhan et al 2019;Xia et al 2020). However, existing solutions on ODA for UAV swarms either fail to address energy efficiency or don't plan trajectories for members of UAV swarms to avoid collisions among UAVs within the swarm.…”

Section: Introductionmentioning

confidence: 99%

“…Existing algorithms for swarm collision avoidance are either energy inefficient or difficult to achieve cooperation. For example, Velocity-based algorithms like Reciprocal Velocity Obstacle (RVO) [9], [10], [11] and Virtual force-based algorithms like Artificial Potential Fields (APF) [12], [13], [14] result in zig-zag trajectories that are energy inefficient to UAVs. Model Predictive Control (MPC)-based methods [15], [16], [17] rely on well-defined control models and parameters of UAVs, which are non-trivial.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

E2Coop: Energy Efficient and Cooperative Obstacle Detection and Avoidance for UAV Swarms

Huang¹,

Zhang²,

Huang

2021

ICAPS

Self Cite

View full text Add to dashboard Cite

Energy efficiency is of critical importance to trajectory planning for UAV swarms in obstacle avoidance. In this paper, we present E2Coop, a new scheme designed to avoid collisions for UAV swarms by tightly coupling Artificial Potential Field (APF) with Particle Swarm Planning (PSO) based trajectory planning. In E2Coop, swarm members perform trajectory planning cooperatively to avoid collisions in an energy-efficient manner. E2Coop exploits the advantages of the active contour model in image processing for trajectory planning. Each swarm member plans its trajectories on the contours of the environment field to save energy and avoid collisions to obstacles. Swarm members that fall within the safeguard distance of each other plan their trajectories on different contours to avoid collisions with each other. Simulation results demonstrate that E2Coop can save energy up to 51% compared with two state-of-the-art schemes.

show abstract

“…A potential field approach is implemented in ref. [24] to find the optimal path for UAVs. The approach is implemented to find the optimal safe, efficient, and smooth trajectory for the UAV at a given altitude using data from a 3D environment.…”

Section: Introductionmentioning

confidence: 99%

Motion planning of unmanned aerial vehicles in dynamic 3D space: a potential force approach

et al. 2022

View full text Add to dashboard Cite

This research focuses on a collision-free real-time motion planning system for unmanned aerial vehicles (UAVs) in complex three-dimensional (3D) dynamic environments based on generalized potential force functions. The UAV must survive in such a complex heterogeneous environment while tracking a dynamic target and avoiding multiple stationary or dynamic obstacles, especially at low hover flying conditions. The system framework consists of two parts. The first part is the target tracking part employing a generalized extended attractive potential force into 3D space. In contrast, the second part is the obstacle avoidance part employing a generalized extended repulsive potential force into 3D space. These forces depend on the relative position and relative velocity between the UAV and respective obstacles. As a result, the UAV is attracted to a moving or stationary target and repulsed away from moving or static obstacles simultaneously in 3D space. Accordingly, it changes its altitude and projected planner position concurrently. A real-time implementation for the system is conducted in the SPACE laboratory to perform motion planning in 3D space. The system performance is validated in real-time experiments using three platforms: two parrot bebop drones and one turtlebot robot. The pose information of the vehicles is estimated using six Vicon cameras during real-time flights. The demonstrated results show the motion planning system’s effectiveness. Also, we propose a successful mathematical solution of the local minima problem associated with the potential field method in both stationary and dynamic environments.

show abstract

A Path Planning Algorithm for Smooth Trajectories of Unmanned Aerial Vehicles via Potential Fields

Cited by 7 publications

References 14 publications

Multi-UAV Collision Avoidance using Multi-Agent Reinforcement Learning with Counterfactual Credit Assignment

Multi-UAV Collision Avoidance using Multi-Agent Reinforcement Learning with Counterfactual Credit Assignment

E2Coop: Energy Efficient and Cooperative Obstacle Detection and Avoidance for UAV Swarms

Motion planning of unmanned aerial vehicles in dynamic 3D space: a potential force approach

Contact Info

Product

Resources

About