Autonomous Controller Design for Unmanned Aerial Vehicles using

  • Slides: 27
Download presentation
Autonomous Controller Design for Unmanned Aerial Vehicles using Multi-objective Genetic Programming Choong K. Oh

Autonomous Controller Design for Unmanned Aerial Vehicles using Multi-objective Genetic Programming Choong K. Oh and Gregory J. Barlow U. S. Naval Research Laboratory North Carolina State University 1

Overview • • 2 Problem Unmanned Aerial Vehicle Simulation Multi-objective Genetic Programming Fitness Functions

Overview • • 2 Problem Unmanned Aerial Vehicle Simulation Multi-objective Genetic Programming Fitness Functions Experiments and Results Conclusions Future Work

Problem Evolve unmanned aerial vehicle (UAV) navigation controllers able to: • Fly to a

Problem Evolve unmanned aerial vehicle (UAV) navigation controllers able to: • Fly to a target radar based only on sensor measurements • Circle closely around the radar • Maintain a stable and efficient flight path throughout flight 3

Controller Requirements • • 4 Autonomous flight controllers for UAV navigation Reactive control with

Controller Requirements • • 4 Autonomous flight controllers for UAV navigation Reactive control with no internal world model Able to handle multiple radar types including mobile radars and intermittently emitting radars Robust enough to transfer to real UAVs

Simulation • To test the fitness of a controller, the UAV is simulated for

Simulation • To test the fitness of a controller, the UAV is simulated for 4 hours of flight time in a 100 by 100 square nmi area • The initial starting positions of the UAV and the radar are randomly set for each simulation trial 5

Sensors • UAVs can sense the angle of arrival (Ao. A) and amplitude of

Sensors • UAVs can sense the angle of arrival (Ao. A) and amplitude of incoming radar signals 6

UAV Control Evolved Controller Sensors Roll angle Autopilot 7 UAV Flight

UAV Control Evolved Controller Sensors Roll angle Autopilot 7 UAV Flight

Transference These controllers should be transferable to real UAVs. To encourage this: • •

Transference These controllers should be transferable to real UAVs. To encourage this: • • • 8 Only the sidelobes of the radar were modeled Noise is added to the modeled radar emissions The angle of arrival value from the sensor is only accurate within ± 10°

Multi-objective GP • • 9 We had four desired behaviors which often conflicted, so

Multi-objective GP • • 9 We had four desired behaviors which often conflicted, so we used NSGA-II (Deb et al. , 2002) with genetic programming to evolve controllers Each fitness evaluation ran 30 trials Each evolutionary run had a population size of 500 and ran for 600 generations Computations were done on a Beowulf cluster with 92 processors (2. 4 GHz)

Functions and Terminals Turns • Hard Left, Hard Right, Shallow Left, Shallow Right, Wings

Functions and Terminals Turns • Hard Left, Hard Right, Shallow Left, Shallow Right, Wings Level, No Change Sensors • Amplitude > 0, Amplitude Slope < 0, Amplitude Slope > 0, Ao. A <, Ao. A > Functions • If. Then, If. Then. Else, And, Or, Not, <, =<, >, >=, > 0, < 0, =, +, -, *, / 10

Fitness Functions Normalized distance • UAV’s flight to vicinity of the radar Circling distance

Fitness Functions Normalized distance • UAV’s flight to vicinity of the radar Circling distance • Distance from UAV to radar when in-range Level time • Time with a roll angle of zero Turn cost • 11 Changes in roll angle greater than 10°

Normalized Distance 12

Normalized Distance 12

Circling Distance 13

Circling Distance 13

Level Time 14

Level Time 14

Turn Cost 15

Turn Cost 15

Performance of Evolution • • 16 Multi-objective genetic programming produces a Pareto front of

Performance of Evolution • • 16 Multi-objective genetic programming produces a Pareto front of solutions, not a single best solution. To gauge the performance of evolution, fitness values for each fitness measure were selected for a minimally successful controller.

Baseline Values Normalized Distance ≤ 0. 15 • Determined empirically Circling Distance • Average

Baseline Values Normalized Distance ≤ 0. 15 • Determined empirically Circling Distance • Average distance less than 2 nmi Level Time • 17 ≥ 1000 ~50% of time (not in-range) with roll angle = 0 Turn Cost • ≤ 4 ≤ 0. 05 Turn sharply less than 0. 5% of the time

Experiments Continuously emitting, stationary radar • Simplest radar case Intermittently emitting, stationary radar •

Experiments Continuously emitting, stationary radar • Simplest radar case Intermittently emitting, stationary radar • Period of 10 minutes, duration of 5 minutes Continuously emitting, mobile radar • • 18 States: move, setup, deployed, tear down In deployed over an hour before moving again

Results Runs Controllers Radar Type Total Succ. Rate Total Avg. Max. Continuously emitting, stationary

Results Runs Controllers Radar Type Total Succ. Rate Total Avg. Max. Continuously emitting, stationary radar 50 45 90% 3, 149 62. 98 170 Intermittently emitting, stationary radar 50 25 50% 1, 891 37. 82 156 Continuously emitting, mobile radar 50 36 72% 2, 266 45. 32 206 19

Continuously emitting, stationary radar 20

Continuously emitting, stationary radar 20

Circling Behavior 21

Circling Behavior 21

Intermittently emitting, stationary radar 22

Intermittently emitting, stationary radar 22

Continuously emitting, mobile radar 23

Continuously emitting, mobile radar 23

Conclusions • • • 24 Autonomous navigation controllers were evolved to fly to a

Conclusions • • • 24 Autonomous navigation controllers were evolved to fly to a radar and then circle around it while maintaining stable and efficient flight dynamics Multi-objective genetic programming was used to evolve controllers Controllers were evolved for three radar types

Future Work Accomplished • Incremental evolution was used to aid in the evolution of

Future Work Accomplished • Incremental evolution was used to aid in the evolution of controllers for more complex radar types and controllers able to handle all radar types • Controllers were successfully tested on a wheeled mobile robot equipped with an acoustic array tracking a speaker 25

Future Work In Progress • Distributed multi-agent controllers will be evolved to deploy multiple

Future Work In Progress • Distributed multi-agent controllers will be evolved to deploy multiple UAVs to multiple radars • Controllers will be tested on physical UAVs for several radar types in field tests next year 26

Acknowledgements • • • 27 This work was done at North Carolina State University

Acknowledgements • • • 27 This work was done at North Carolina State University and the U. S. Naval Research Laboratory Financial support was provided by the Office of Naval Research Computational resources were provided by the U. S. Naval Research Laboratory