You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

CozmoAgent.cs 6.0KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184
  1. using MLAgents;
  2. using OpenCvSharp;
  3. using System;
  4. using System.Collections;
  5. using System.Collections.Generic;
  6. using UnityEngine;
  7. public class CozmoAgent : Agent
  8. {
  9. // Possible Actions
  10. private const int STOP = 0;
  11. private const int FORWARD = 1;
  12. private const int RIGHT = 2;
  13. private const int LEFT = 3;
  14. // Used to determine different areas in the image (near to the center, far away)
  15. private const float NEAR_AREA_PERCENTAGE_OFFSET = 0.2f;
  16. private const float FAR_AREA_PERCENTAGE_OFFSET = 0.3f;
  17. [Tooltip("The virtual Cozmo camera")]
  18. public Camera renderCamera;
  19. //[Tooltip("Final cropped and scaled rendertexture")]
  20. //public RenderTexture renderTextureScaled;
  21. [Tooltip("Reference to the CozmoMovement script")]
  22. public CozmoMovementController movementController;
  23. public float timeBetweenDecisionsAtInference;
  24. private Academy academy; // CozmoAcademy
  25. private float timeSinceDecision; // time since last decision
  26. private ImageProcessor imageProcessor; // reference to the ImageProcessor
  27. private int nearAreaLimit = 0; // X coordinate limit for the near to the imagecenter area
  28. private int farAreaLimit = 0; // X coordinate limit for the far away to the imagecenter area
  29. private void Start()
  30. {
  31. academy = FindObjectOfType(typeof(CozmoAcademy)) as CozmoAcademy;
  32. imageProcessor = renderCamera.GetComponent<ImageProcessor>();
  33. nearAreaLimit = (int)(renderCamera.targetTexture.width / 2 * NEAR_AREA_PERCENTAGE_OFFSET);
  34. farAreaLimit = (int)(renderCamera.targetTexture.width / 2 * FAR_AREA_PERCENTAGE_OFFSET);
  35. }
  36. public void FixedUpdate()
  37. {
  38. WaitTimeInference();
  39. }
  40. // to be implemented by the developer
  41. public override void AgentAction(float[] vectorAction, string textAction)
  42. {
  43. //print("Action before FloorToInt: " + vectorAction[0]);
  44. int action = Mathf.FloorToInt(vectorAction[0]);
  45. Point centerOfGravity = imageProcessor.CenterOfGravity;
  46. //Vector3 targetPos = transform.position;
  47. //print("Action after FloorToInt: " + action);
  48. AddReward(-0.01f);
  49. switch (action)
  50. {
  51. case STOP:
  52. movementController.currentMovementState = MovementState.Stop;
  53. break;
  54. case FORWARD:
  55. movementController.currentMovementState = MovementState.Forward;
  56. break;
  57. case RIGHT:
  58. movementController.currentMovementState = MovementState.Right;
  59. break;
  60. case LEFT:
  61. movementController.currentMovementState = MovementState.Left;
  62. break;
  63. default:
  64. //movement.Move(0);
  65. throw new ArgumentException("Invalid action value. Stop movement.");
  66. }
  67. // Render new image after movement in order to update the centerOfGravity
  68. if (renderCamera != null)
  69. {
  70. renderCamera.Render();
  71. }
  72. RewardAgent();
  73. imageProcessor.enabled = false;
  74. }
  75. /// <summary>
  76. /// TODO: Cleanup code
  77. /// </summary>
  78. private void RewardAgent()
  79. {
  80. float centerOfImageX = renderCamera.targetTexture.width / 2;
  81. float centerOfGravityX = imageProcessor.CenterOfGravity.X;
  82. float reward = 0;
  83. // Center of gravity is far left of the center
  84. if (centerOfGravityX <= centerOfImageX - farAreaLimit)
  85. {
  86. reward = -1;
  87. }
  88. // Center of gravity is between far and near left of the center
  89. else if (centerOfGravityX <= centerOfImageX - nearAreaLimit)
  90. {
  91. float range = (centerOfImageX - nearAreaLimit) - (centerOfImageX - farAreaLimit);
  92. float distanceToLeftFarBorder = centerOfGravityX - (centerOfImageX - farAreaLimit);
  93. reward = -(1 - (distanceToLeftFarBorder / range));
  94. }
  95. // Center of gravity is near left of the center
  96. else if (centerOfGravityX <= centerOfImageX)
  97. {
  98. float range = centerOfImageX - (centerOfImageX - nearAreaLimit);
  99. float distanceToLeftFarBorder = centerOfGravityX - (centerOfImageX - nearAreaLimit);
  100. reward = (distanceToLeftFarBorder / range);
  101. }
  102. // Center of gravity is far right of the center
  103. else if (centerOfGravityX >= centerOfImageX + farAreaLimit)
  104. {
  105. reward = -1;
  106. }
  107. // Center of gravity is between far and near right of the center
  108. else if (centerOfGravityX >= centerOfImageX + nearAreaLimit)
  109. {
  110. float range = (centerOfImageX + farAreaLimit) - (centerOfImageX + nearAreaLimit);
  111. float distanceToLeftFarBorder = centerOfGravityX - (centerOfImageX + nearAreaLimit);
  112. reward = -(distanceToLeftFarBorder / range);
  113. }
  114. // Center of gravity is near right of the center
  115. else if (centerOfGravityX >= centerOfImageX)
  116. {
  117. float range = (centerOfImageX + nearAreaLimit) - centerOfImageX;
  118. float distanceToLeftFarBorder = centerOfGravityX - centerOfImageX;
  119. reward = (1 - distanceToLeftFarBorder / range);
  120. }
  121. SetReward(reward);
  122. }
  123. // to be implemented by the developer
  124. public override void AgentReset()
  125. {
  126. academy.AcademyReset();
  127. }
  128. private void OnTriggerEnter(Collider other)
  129. {
  130. if (other.transform.CompareTag("Goal"))
  131. {
  132. print("Collission");
  133. Done();
  134. }
  135. }
  136. private void WaitTimeInference()
  137. {
  138. if (renderCamera != null)
  139. {
  140. renderCamera.Render();
  141. }
  142. if (!academy.GetIsInference())
  143. {
  144. RequestDecision();
  145. }
  146. else
  147. {
  148. if (timeSinceDecision >= timeBetweenDecisionsAtInference)
  149. {
  150. timeSinceDecision = 0f;
  151. RequestDecision();
  152. }
  153. else
  154. {
  155. timeSinceDecision += Time.fixedDeltaTime;
  156. }
  157. }
  158. }
  159. }