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 5.3KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162
  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 = 0.3f;
  16. [Tooltip("The virtual Cozmo camera")]
  17. public Camera renderCamera;
  18. [Tooltip("Reference to the CozmoMovement script")]
  19. public CozmoMovementController movementController;
  20. public float timeBetweenDecisionsAtInference;
  21. private Academy academy; // CozmoAcademy
  22. private float timeSinceDecision; // time since last decision
  23. private ImageProcessor imageProcessor; // reference to the ImageProcessor
  24. private int nearAreaLimit = 0; // X coordinate limit for the near to the imagecenter area
  25. private int centerOfImageX = 0; // Middle of the image in x direction
  26. private void Start()
  27. {
  28. academy = FindObjectOfType(typeof(CozmoAcademy)) as CozmoAcademy;
  29. imageProcessor = renderCamera.GetComponent<ImageProcessor>();
  30. nearAreaLimit = (int)(renderCamera.targetTexture.width / 2 * NEAR_AREA_PERCENTAGE_OFFSET);
  31. centerOfImageX = renderCamera.targetTexture.width / 2;
  32. }
  33. public void FixedUpdate()
  34. {
  35. WaitTimeInference();
  36. }
  37. // to be implemented by the developer
  38. public override void AgentAction(float[] vectorAction, string textAction)
  39. {
  40. int action = Mathf.FloorToInt(vectorAction[0]);
  41. Point centerOfGravity = imageProcessor.CenterOfGravity;
  42. AddReward(-0.01f);
  43. switch (action)
  44. {
  45. case STOP:
  46. movementController.currentMovementState = MovementState.Stop;
  47. break;
  48. case FORWARD:
  49. movementController.currentMovementState = MovementState.Forward;
  50. break;
  51. case RIGHT:
  52. movementController.currentMovementState = MovementState.Right;
  53. break;
  54. case LEFT:
  55. movementController.currentMovementState = MovementState.Left;
  56. break;
  57. default:
  58. //movement.Move(0);
  59. throw new ArgumentException("Invalid action value. Stop movement.");
  60. }
  61. // Render new image after movement in order to update the centerOfGravity
  62. if (renderCamera != null)
  63. {
  64. renderCamera.Render();
  65. }
  66. RewardAgent();
  67. }
  68. // Set the reward for the agent based on how far away the center of gravity is from the center of the image
  69. private void RewardAgent()
  70. {
  71. float centerOfGravityX = imageProcessor.CenterOfGravity.X;
  72. float reward = 0;
  73. // Center of gravity is far away from the center (left)
  74. if (centerOfGravityX <= centerOfImageX - nearAreaLimit)
  75. {
  76. float range = centerOfImageX - nearAreaLimit;
  77. reward = -(1 - (centerOfGravityX / range));
  78. // Clamp the reward to max -1 in order to handle rewards if the center of gravity is outside of the image
  79. reward = Mathf.Clamp(reward, -1, 0);
  80. }
  81. // Center of gravity is near left of the center
  82. else if (centerOfGravityX <= centerOfImageX)
  83. {
  84. float range = centerOfImageX - (centerOfImageX - nearAreaLimit);
  85. float distanceToLeftFarBorder = centerOfGravityX - (centerOfImageX - nearAreaLimit);
  86. reward = (distanceToLeftFarBorder / range);
  87. }
  88. // Center of gravity is far away from the center (right)
  89. else if (centerOfGravityX >= centerOfImageX + nearAreaLimit)
  90. {
  91. float range = renderCamera.targetTexture.width - (centerOfImageX + nearAreaLimit);
  92. reward = -(((centerOfGravityX - (centerOfImageX + nearAreaLimit)) / range));
  93. // Clamp the reward to max -1 in order to handle rewards if the center of gravity is outside of the image
  94. reward = Mathf.Clamp(reward, -1, 0);
  95. }
  96. // Center of gravity is near right of the center
  97. else if (centerOfGravityX >= centerOfImageX)
  98. {
  99. float range = (centerOfImageX + nearAreaLimit) - centerOfImageX;
  100. float distanceToCenterOfImage = centerOfGravityX - centerOfImageX;
  101. reward = (1 - distanceToCenterOfImage / range);
  102. }
  103. SetReward(reward);
  104. }
  105. // to be implemented by the developer
  106. public override void AgentReset()
  107. {
  108. academy.AcademyReset();
  109. }
  110. private void OnTriggerEnter(Collider other)
  111. {
  112. if (other.transform.CompareTag("Goal"))
  113. {
  114. Done();
  115. }
  116. }
  117. private void WaitTimeInference()
  118. {
  119. if (renderCamera != null)
  120. {
  121. renderCamera.Render();
  122. }
  123. if (!academy.GetIsInference())
  124. {
  125. RequestDecision();
  126. }
  127. else
  128. {
  129. if (timeSinceDecision >= timeBetweenDecisionsAtInference)
  130. {
  131. timeSinceDecision = 0f;
  132. RequestDecision();
  133. }
  134. else
  135. {
  136. timeSinceDecision += Time.fixedDeltaTime;
  137. }
  138. }
  139. }
  140. }