Bayesian‐Based Domain Search Using Multiple Autonomous Vehicles with Intermittent Information Sharing

This paper deals with a UAV path planning problem in the environment where both solid obstacles and soft obstacles exist. The artificial potential field approach is updated by introducing an additional control force and integrating it with the concept of receding horizon control for UAV trajectory optimization. The original problem is converted into a multi-objective optimization problem by regarding the involved additional control term as the optimization variable. Seeing as the establishment of an additional control force of soft obstacles is dependent on the probability of certain specifications such as survivability, the additional control term accomplishes the description of the specified property index better than those that have been considered in the past, such as distance and control energy. The optimal solution to the path planning problem, in terms of the additional control force method, and the computational efficiency according to the receding horizon control, both contribute to the proposed algorithm. Meanwhile, the proposed method is able to protect the UAV from local minima of additional control force. The numerical examples verify the advantages of this approach.

Section: Construction Of Uav Dynamics Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

UAV Path Planning in Mixed‐Obstacle Environment via Artificial Potential Field Method Improved by Additional Control Force

Luo¹,

Yu²,

Mei³

et al. 2014

“…Autonomous vehicles are developed to achieve fully autonomous driving in everyday life. Recently, there have been numerous research efforts to tackle related issues for implementing autonomous vehicles [1–3]. Autonomous parking is one of important autonomous applications and will be implemented in the near future.…”

Section: Introductionmentioning

confidence: 99%

Human‐like motion planning for autonomous parking based on revised bidirectional rapidly‐exploring random tree* with Reeds‐Shepp curve

Jhang

Lian

Hao

2020

Autonomous parking is one significant autonomous application and will be implemented in daily life in the near future. Due to encountered narrow environments, the issues related to autonomous parking, such as path quality requirements, strict collision avoidance, and motion direction changes, must be overcome properly. Moreover, to be applied in daily driving activities, real‐time planning and human preference should be fulfilled by the designed motion planners. Therefore, an efficient and human‐like motion planning method based on the revised Bidirectional Rapidly‐Exploring Random Tree* (Bi‐RRT*) with Reeds‐Shepp curve is presented. The proposed method results in human‐like paths which have high trajectory quality and consistency for parking scenarios due to the revised Bi‐RRT* framework. Strict collision checking model guarantees the resulting paths to be collision‐free and even leaves safe distance from obstacles and uncertainties. State space adjustment makes the path optimization more efficient and effective. On the other hand, the cost function revision makes the resulting paths meet human driving behavior, such as less backward driving and motion direction changes. In addition, rigorous simulations and analysis demonstrate the effectiveness of the cost function revision and the state space adjustment and illustrate good performance of the proposed approach in common and even complex parking scenarios.

“…In this paper, we consider the problem of persistent coverage and we present a new method where the agents' paths and actions are computed online in a partially distributed manner. Although some works focus on uncertainty maps with intermittent communications or constraining the motion to maintain the communication network , we consider that the coverage information of the domain is available for all the agents, whereas the coverage and motion actions are computed locally by each agent resulting in a partially distributed system. This type of topology has been previously used, for instance in .…”

Section: Introductionmentioning

confidence: 99%

Adaptive Action for Multi‐Agent Persistent Coverage

Franco¹,

López‐Nicolás²,

Sagüés³

et al. 2015

Persistent coverage with a team of agents refers to the task of covering an area where the coverage degrades with time. This is a dynamic task as opposed to the deployment problem. A key issue here is the coverage degradation that prevents the complete coverage fulfilment and requires persistence in the action. We propose a new method for persistent coverage where the agents' actions are computed in a partially distributed manner. The contribution is a control strategy based on variable coverage action and variable coverage range of the agents. This control provides adaptive behaviour in terms of actuator power and actuator domain in order to reduce the coverage error and energy consumption. The proposal is tested in simulation, showing clear improvement in terms of efficiency, flexibility, and scalability.