Spatiotemporal scenario data-driven decision for the path planning of multiple UASs

Can Model Checking Assure, Distributed Autonomous Systems Agree? An Urban Air Mobility Case Study

“…Property 10 : A drone with a malfunctioned sensor should not be chosen to serve a request E <> ((technical sensor[0] == f alse && Drone1.Make Decision) OR (technical sensor [1] ==false && Drone2.Make Decision) OR (technical sensor [2]==false && Drone3.Make Decision)) Through this requirement we try to investigate if there exists a path eventually, where a drone whose sensor has been malfunctioned or is not working properly, is chosen to serve the request. The requirement stated as property keeps on running until server connection is lost indicating it is unable to find such path for the number of states it runs.…”

“…Additionally, communication capabilities have enabled the use of multiple autonomous systems to be used for executing autonomous missions. Unmanned Aerial Systems (UAS) are used across diverse applications, such as structural health monitoring [1], data driven path planning [2], and object classification [3]. Research by Cesare and Hollinger presented in [4] explores execution of multi-UAS missions under unreliable communication and limited battery life, for search and rescue applications that include urban search and rescue, military reconnaissance, and underground mine rescue operations.…”

Integral reinforcement learning‐based approximate minimum time‐energy path planning in an unknown environment

“…Optimal path planning in a complex environment has thus attracted significant attentions. For example, some studies extended the Zermelo's problem to unmanned aerial vehicle (UAV) path planning in wind fields, including constant, 16 time‐varying, 17 spatially varying, 18 and spatiotemporally varying winds 19‐21 . Some other studies extended the Dubins path solution in the presence of constant 22‐24 and time‐varying winds 25 …”

“…This is usually not the case in real applications, due to the existence of uncertainty in weather forecasts. Online adaptive path planning becomes valuable, as it only relies on measurement (or estimation) of real‐time environment information through either on‐board sensors or weather services 20,21,26 . In Reference 27, a shortest time path was first calculated under a known constant wind, and then a spatial sliding surface controller was adopted to handle small unknown disturbances.…”