Gregory J. Barlow March 19, 2004

1. Gregory J. Barlow March 19, 2004 Design of Autonomous Navigation Controllers for Unmanned Aerial Vehicles using Multi-objective Genetic Programming

2. Overview • Background • Unmanned Aerial Vehicle Control • Evolution and Fitness Evaluation • Experiments and Results • Conclusions and Future Work

3. Evolutionary Computation • Biologically inspired computational method of problem solving • May be applied to a variety of structures (binary strings, real numbers, computer programs, hardware, neural networks, etc) because the algorithm operates on an encoding of the parameters, not the parameters themselves

4. Genetic Programming • A population of random programs is created • Each individual in the population undergoes a fitness test and is assigned a fitness value • Genetic operators (crossover, mutation, etc) are performed on the population to form the next generation • The process is repeated until a suitable individual is evolved

5. Population Child(ren) Genetic Operator Evaluation Parent(s) Selection Evolutionary Process

6. Representation • Each individual is a program, which we represent as a tree • Function set: for non-leaf nodes • Terminal set: for leaf nodes

7. Crossover

8. Mutation

9. Unmanned Aerial Vehicle Control • Create controllers that will fly a UAV toward a target radar and then circle the radar for jamming • Make the UAV controller completely autonomous • Be able to handle multiple radar types • Be able to transfer evolve controllers to real UAVs

10. 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 position of the UAV is randomly set along the bottom of the simulation space • The position of the radar is also randomly set for each simulation • UAVs can sense the AoA and amplitude of incoming radar signals

11. Simulation

12. Transference • These controllers should be transferable to real UAVS. To encourage this: • 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°

13. Functions and Terminals • Hard Left, Hard Right, Shallow Left, Shallow Right, Wings Level, No Change • IfThen, IfThenElse, And, Or, Not, <, =<, >, >=, > 0, < 0, =, +, -, *, / • Amplitude > 0, Amplitude Slope < 0, Amplitude Slope > 0, AoA <, AoA >

14. Fitness Functions • Normalized distance • Circling distance • Level time • Turn cost

15. Normalized Distance

16. Circling Distance

17. Level Time

18. Turn Cost

19. Performance of Evolution • Multi-objective genetic programming produces a Pareto-optimal 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.

20. Baseline Values Normalized Distance 0.15 Circling Distance 4 Level Time 1000 Turn Cost 0.05

21. Direct Evolution Experiments • Continuously emitting, stationary radar • Intermittently emitting, stationary radar with a regular period • Intermittently emitting, stationary radar with an irregular period • Continuously emitting, mobile radar • Intermittently emitting, mobile radar with a regular period

22. Direct Evolution

23. Continuously emitting, stationary radar

24. Circling Behavior

25. Intermittently emitting, stationary (regular)

26. Intermittently emitting, stationary (irregular)

27. Continuously emitting, mobile radar

28. Intermittently emitting, mobile radar

29. Incremental Evolution • Continuously emitting, stationary radar (seed populations) • Intermittently emitting, stationary radar • Continuously emitting, mobile radar • Intermittently emitting, stationary radar (multiple increments) • Intermittently emitting, mobile radar (multiple increments)

30. Incremental Evolution

31. Intermittent, mobile (multiple increments)

32. Transference to a wheeled mobile robot • Controllers were designed for UAVs • A UAV was not yet available for flight tests to evaluate transference • Evolved controllers were tested on a wheeled mobile robot, the EvBot II • A speaker was used in place of the radar, and an acoustic array in place of the radar sensor

33. EvBot II • PC/104 processor • Communications with a wireless network card • Runs Linux • On-board acoustic array

34. Transference considerations • In simulation, the sensor accuracy was ±10°, but the acoustic array accuracy was approximately ±45° • Wheeled robot not controlled by roll angle, must be turned and then moved • The size of the maze environment was not equivalent to the simulation environment, instead the scale size of the maze environment was 1.13 by 0.9 nautical miles

35. Sensor accuracy Sensor accuracy of ± 10° Sensor accuracy of ± 45°

36. Controller 1

37. Controller 2

38. Conclusions • 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 five radar types using both direct evolution and incremental evolution

39. Conclusions • Incremental evolution dramatically increased the success rates for the more difficult radar types • Methods were used to aid in transference of controllers to real UAVs • Controllers were tested on a wheeled mobile robot with good success • Evolved controllers are capable of transference to real physical vehicles

40. Future Work • Controllers will be tested on physical UAVs for several radar types • Distributed multi-agent controllers will be evolved to handle cases of multiple UAVs against multiple radars • Incremental evolution will be used to aid in the evolution of fit multi-agent controllers for complex radar types