Vision-Based Collision Avoidance for Personal Aerial Vehicles Using Dynamic Potential Fields

Abstract

In this paper we present a prototype system that aids the operator of a Personal Air Vehicle (PAV) by actively monitoring vehicle surroundings and providing autonomous control inputs for obstacle avoidance. The prototype is developed for a Personal Air Transportation System (PATS) that will enable human operators with low level of technical knowledge to use aerial vehicles for a day-to-day commute. While most collision avoidance systems used on human controlled vehicles override operator input, our proposed system allows the operator to be in control of the vehicle at all times. Our approach uses a dynamic potential field to generate pseudo repulsive forces that, when converted into control inputs, force the vehicle on a trajectory around the obstacle. By allowing the vehicle control input to be the sum of operator controls and collision avoidance controls, the system ensures that the operator is in control of the vehicle at all times. We first present a dynamic repulsive potential function and then provide a generic control architecture required to implement the collision avoidance system on a mobile platform. Further, extensive computer simulations of the proposed algorithm are performed on a quadcopter model, followed by hardware experiments on a stereo vision sensor. The proposed collision avoidance system is computationally inexpensive and can be used with any sensor that can produce a point cloud for obstacle detection.

Collision Detection and Avoidance for Underwater Vehicles Using Omnidirectional Vision

“…The distances are used to generate repulsive forces to control the behavior of the robot. A vision-based collision avoidance system for UAVs was proposed by [ 42 ], using a dynamic potential field to repel the vehicle away from hazards. Perez et al.…”

“…The distances are used to generate repulsive forces to control the behavior of the robot. A vision-based collision avoidance system for UAVs was proposed by [42], using a dynamic potential field to repel the vehicle away from hazards. Perez et al [43] made use of a stereoscopic system to compute a disparity map from images provided by the stereo camera and located zones free of obstacles to guide a multi-copter onto collision-free trajectories.…”

Neighbor Reward with Optimal Reciprocal Collision Avoidance for Swarm Agents*

“…In our previous work [15], the obstacle avoidance strategy is wall following, based on artificial potential field. According to the distance from obstacles and goal of agent A, we get the repulsion/attractions which could deduce the velocity for agent A avoiding collisions [16][17][18]. Nevertheless, with the potential function, agents' movements tend to be zigzag due to the kinematics and dynamics of agents.…”

Collision Avoidance for Cooperative UAVs with Rolling Optimization Algorithm Based on Predictive State Space

“…Based on the consideration above, some researchers adjust the heading direction of UAVs and keep a constant velocity to avoid collision [15,18]. UAV collision avoidance methods are proposed by varying heading, velocity, or both [14,19,20]. However, the method sets the UAVs at constant altitude, which limits the practical use of the method.…”

“…In terms of UAVs, relevant research is growing at a fantastic speed to realize the purpose of "free flight" [13], which has been the main issue for UAV mission implementation. Normally, assumptions that cooperative UAVs can communicate their positions, speed, heading, waypoints, and proposed trajectories are allowed [14,15]. With the airspace density increasing, centralized methods are more computationally expensive to solve the UAVs' collision avoidance problem.…”