Learning-‘N-Flying: A Learning-Based, Decentralized Mission-Aware UAS Collision Avoidance Scheme

  title={Learning-‘N-Flying: A Learning-Based, Decentralized Mission-Aware UAS Collision Avoidance Scheme},
  author={Alena Rodionova and Yash Vardhan Pant and Connor Kurtz and Kuk Jin Jang and Houssam Abbas and Rahul Mangharam},
  journal={ACM Transactions on Cyber-Physical Systems (TCPS)},
  pages={1 - 26}
Urban Air Mobility, the scenario where hundreds of manned and Unmanned Aircraft Systems (UASs) carry out a wide variety of missions (e.g., moving humans and goods within the city), is gaining acceptance as a transportation solution of the future. One of the key requirements for this to happen is safely managing the air traffic in these urban airspaces. Due to the expected density of the airspace, this requires fast autonomous solutions that can be deployed online. We propose Learning-‘N-Flying… 


Learning-to-Fly: Learning-based Collision Avoidance for Scalable Urban Air Mobility
This work develops L2F, a two-stage collision avoidance method that consists of a learning-based decision-making scheme and a distributed, linear programming-based UAS control algorithm and shows the real-time applicability of the method which is faster than the MILP approach and can resolve 100% of collisions when there is ample room to maneuver, and shows graceful degradation in performance otherwise.
Design and implementation of a centralized system for autonomous unmanned aerial vehicle trajectory conflict resolution
This work proposes a centralized, infrastructure-tovehicle (I2V) approach that leverages modular embedded systems (“control modules”) and implements a voxel-based airspace reservation system that interrogates and retrieves the stored trajectories from aUAVs approaching the reservation airspace.
Fly-by-Logic: Control of Multi-Drone Fleets with Temporal Logic Objectives
This paper presents an approach to solve the problem of safe planning and control for multi-drone systems across a variety of missions by maximizing robustness to generate trajectories for the quadrotors that satisfy the STL specification in continuous-time.
DRONA: A Framework for Safe Distributed Mobile Robotics
This paper presents a novel and provably correct decentralized asynchronous motion planner that can perform on-the-fly collision-free planning for dynamically generated tasks and formalizes the DMR system as a mixed-synchronous system.
A Distributed Approach for Collision Avoidance between Multirotor UAVs Following Planned Missions
Experimental and simulation results demonstrated the validity and effectiveness of the MBCAP, a novel UAV collision avoidance protocol applicable to all types of multicopters flying autonomously that relies on wireless communications in order to detect nearby UAVs, and to negotiate the procedure to avoid any potential collision.
Collision avoidance for aerial vehicles in multi-agent scenarios
This article describes an investigation of local motion planning, or collision avoidance, for a set of decision-making agents navigating in 3D space, which builds on the concept of velocity obstacles, which characterizes the set of trajectories that lead to a collision between interacting agents.
Vehicle to Vehicle (V2V) communication for Collision avoidance for Multi-copters flying in UTM –TCL4
It is shown how V2V communication can be used for feasible, collision-free paths for multi agent systems and an end to end simulation study shows the use of V 2V communication for UTM TCL4 deployment.
Linear temporal logic vehicle routing with applications to multi‐UAV mission planning
Missions with high combinatorial complexity involving several logical and temporal constraints often arise in cooperative control of multiple Uninhabited Aerial Vehicles. In this paper, we propose a
An introduction to ACAS Xu and the challenges ahead
This work proposes an introduction to the ACAS Xa/Xu common basis, as it is unlikely to change, including the general architecture and Collision Avoidance (CA) logics, followed by a presentation of concepts specific to ACAS Xu.
Collision-Free Reactive Mission and Motion Planning for Multi-robot Systems
This paper describes a holistic method for automatically synthesizing controllers for a team of robots operating in an environment shared with other agents that enables scalability of the high-level plan synthesis with respect to dynamic obstacles and enforces correctness of the low-level motion.