learning how to soar learning how to soar
play

Learning How to Soar Learning How to Soar Terrence Sejnowski Salk - PowerPoint PPT Presentation

Learning How to Soar Learning How to Soar Terrence Sejnowski Salk Institute UCSD Bird Migration Bird Migration Migration Ecology of Birds, Ian Newton Thermal Soaring Thermal Soaring Rayleigh-Bnard Convection Rayleigh-Bnard Convection


  1. Learning How to Soar Learning How to Soar Terrence Sejnowski Salk Institute UCSD

  2. Bird Migration Bird Migration Migration Ecology of Birds, Ian Newton

  3. Thermal Soaring Thermal Soaring

  4. Rayleigh-Bénard Convection Rayleigh-Bénard Convection

  5. Atmospheric Turbulence Atmospheric Turbulence

  6. Tracking a Falcon with GPS Tracking a Falcon with GPS

  7. Humans Soar Too Humans Soar Too

  8. Glider Aerodynamics Bank angle 1 - male condor 2- female condor 3 - black vulture 4 - caracara 4 2 3 1 Angle of attack Control over bank angle and angle of attack Shephard & Lambertucci, 2013

  9. How do Birds Find and Navigate Thermals? How do Birds Find and Navigate Thermals? What quantities do birds sense? • Vertical velocities, temperature, gradients, etc? • How should the bird respond to these cues? • Experiments are hard to control and strategies are difficult to infer from limited data Physics simulations are complex and there are many variables. What should an optimal agent sense?

  10. Time is Honey

  11. Karl von Frisch

  12. Temporal Difference Learning Temporal Difference Learning TD - error :      r V ( s ) V ( s )   t t 1 t 1 t Actions are determined by preference s :   p ( s , a ) e      ( s , a ) Pr a a s s ,  t t t p ( s , b ) e b Update the preference s :     p ( s , a ) p ( s , a ) t t t t t The value function update : Sutton and Barto, 1988     V ( s ) V ( s ) t t t

  13. Hammer and Menzel, 1997 VUMmx1 - Octopamine

  14. Temporal Difference Learning Temporal Difference Learning Montague, Dayan and Sejnowski, 1994

  15. Actor Critic Model Actor Critic Model Dopamine Neurons Dopamine Neurons Environment Cerebral Cortex Basal Reward Ganglia Prediction Error Dopamine Montague, Dayan and Sejnowski, 1996

  16. Temporal Difference Learning Temporal Difference Learning Go Defeat, 2017 Go Defeat, 2017 Environment Cerebral Ke Jie Ke Jie Cortex Basal Reward Ganglia Prediction Error DeepMind DeepMind Dopamine

  17. What Do Thermals Look Like? What Do Thermals Look Like? Rayleigh-Benard convection Vertical velocity field Temperature field Reddy, Vergassola, Sejnowski, 2017

  18. Sink or Soar? Sink or Soar? Pre-training Post-training

  19. Learned Policy Learned Policy +5 o 1-2 meters 0 o -5 o v z  Vertical velocity gradient a z Vertical acceleration

  20. Conclusions Conclusions angle of attack vertical acceleration a z and a z and v z gradients v z gradients v z gradients across wings across wings are useful are useful climb rate temperature control over control over angle of attack angle of attack is not useful is not useful

  21. Field Experiments Field Experiments

  22. GoPro Glider GoPro Glider

  23. Gautam Reddy Field Experiments Field Experiments

  24. Field Experiments Field Experiments observed desired 30 Bank angle ( o ) 0 -30 0 50 100 Time (s)

  25. Measuring the Vertical Wind Velocity Measuring the Vertical Wind Velocity GPS and barometer measurement give vertical ground velocity We need to estimate wind velocity GPS/baro ground vel. = wind vel. + glider’s air vel. Pitch( o ) 8 modeling -8 Phugoid 20 s

  26. Training a Glider in the Field Training a Glider in the Field Reddy, Vergassola, Sejnowski, 2018

  27. Training a Glider in the Field Training a Glider in the Field

  28. Field Experiments Field Experiments

  29. Thank You Peter Dayan Gautam Reddy Read Montague Massimo Vergassola John Doyle

Recommend


More recommend