unity-tech-cn
/
ml-agents
46
14
派生 39
代码 合并请求 版本发布
浏览代码

added dirIndicator and orentCubeGizmo

/docs-update
Hunter-Unity 5 年前
当前提交
81e976ac
共有 5 个文件被更改，包括 270 次插入 和 2010 次删除
  1. 2
      Project/Assets/ML-Agents/Examples/SharedAssets/Resources/OrientationCube.prefab
  2. 957
      Project/Assets/ML-Agents/Examples/Walker/Prefabs/DynamicPlatformWalker.prefab
  3. 998
      Project/Assets/ML-Agents/Examples/Walker/Scenes/WalkerDynamic.unity
  4. 318
      Project/Assets/ML-Agents/Examples/Walker/Scripts/WalkerAgentDynamic.cs
  5. 5
      Project/Assets/ML-Agents/Examples/WallJump/Materials/TransparentWall.mat

2
Project/Assets/ML-Agents/Examples/SharedAssets/Resources/OrientationCube.prefab
查看文件


m_Icon: {fileID: 0}
m_NavMeshLayer: 0
m_StaticEditorFlags: 0
m_IsActive: 1
m_IsActive: 0
--- !u!4 &2591864625898824440
Transform:
m_ObjectHideFlags: 0

957
Project/Assets/ML-Agents/Examples/Walker/Prefabs/DynamicPlatformWalker.prefab
文件差异内容过多而无法显示
查看文件

998
Project/Assets/ML-Agents/Examples/Walker/Scenes/WalkerDynamic.unity
文件差异内容过多而无法显示
查看文件

318
Project/Assets/ML-Agents/Examples/Walker/Scripts/WalkerAgentDynamic.cs
查看文件


using Unity.MLAgents;
using Unity.MLAgentsExamples;
using Unity.MLAgents.Sensors;
using UnityEditor;
using BodyPart = Unity.MLAgentsExamples.BodyPart;
[Header("Walking Speed")]
[Space(10)]
public float maximumWalkingSpeed = 999; //The max walk velocity magnitude an agent will be rewarded for
[Header("Orientation Cube")]
[Space(10)]
//This will be used as a stable observation platform for the ragdoll to use.
GameObject m_OrientationCube;
public bool showOrientationCubeGizmo = true;
public Transform directionIndicator;
Vector3 m_WalkDir;
Quaternion m_WalkDirLookRot;
public float targetSpawnRadius;
public float targetSpawnRadius;
[Header("Walk Direction Worldspace")]
// public Vector3 walkDirWorldspace = Vector3.right;
//ORIENTATION
Vector3 m_WalkDir;
Quaternion m_WalkDirLookRot;
Matrix4x4 m_worldPosMatrix;
[Header("Body Parts")]
[Space(10)]
public Transform hips;
public Transform chest;
public Transform spine;

Rigidbody m_SpineRb;
EnvironmentParameters m_ResetParams;
private GameObject m_OrientationCube;
public Quaternion cubeRotation;
public Quaternion hipsRotation;
//Spawn an orientation cube
// m_OrientationCube.transform.SetParent(transform.parent);
UpdateOrientationCube();
m_JdController = GetComponent<JointDriveController>();

//GROUND CHECK
sensor.AddObservation(bp.groundContact.touchingGround ? 1 : 0); // Is this bp touching the ground
// //RELATIVE RB VELOCITY
// var velocityRelativeToLookRotationToTarget = m_worldPosMatrix.inverse.MultiplyVector(bp.rb.velocity);
// sensor.AddObservation(velocityRelativeToLookRotationToTarget);
//
// //RELATIVE RB ANGULAR VELOCITY
// var angularVelocityRelativeToLookRotationToTarget = m_worldPosMatrix.inverse.MultiplyVector(bp.rb.angularVelocity);
// sensor.AddObservation(angularVelocityRelativeToLookRotationToTarget);
//RELATIVE RB VELOCITIES --WAS
// sensor.AddObservation(m_OrientationCube.transform.InverseTransformVector(bp.rb.velocity));
// sensor.AddObservation(m_OrientationCube.transform.InverseTransformVector(bp.rb.angularVelocity));
sensor.AddObservation(m_OrientationCube.transform.InverseTransformDirection(bp.rb.velocity)); //best if cube fixed rot?
sensor.AddObservation(m_OrientationCube.transform.InverseTransformDirection(bp.rb.angularVelocity)); //best if cube fixed rot?
// sensor.AddObservation(bp.rb.velocity - m_JdController.bodyPartsDict[hips].rb.velocity);
// sensor.AddObservation(bp.rb.angularVelocity - m_JdController.bodyPartsDict[hips].rb.angularVelocity);
//Get velocities in the context of our orientation cube's space
//Note: You can get these velocities in world space as well but it may not train as well.
sensor.AddObservation(m_OrientationCube.transform.InverseTransformDirection(bp.rb.velocity));
sensor.AddObservation(m_OrientationCube.transform.InverseTransformDirection(bp.rb.angularVelocity));
// sensor.AddObservation(bp.rb.velocity);
// sensor.AddObservation(bp.rb.angularVelocity);
// var localPosRelToHips = hips.InverseTransformPoint(rb.position);
// sensor.AddObservation(localPosRelToHips);
// sensor.AddObservation(m_OrientationCube.transform.InverseTransformPointUnscaled(bp.rb.position));
// sensor.AddObservation(hips.InverseTransformPointUnscaled(bp.rb.position));
// if (bp.rb.transform != hips && bp.rb.transform != handL && bp.rb.transform != handR &&
// bp.rb.transform != footL && bp.rb.transform != footR && bp.rb.transform != head)
// if (bp.rb.transform != hips && bp.rb.transform != handL && bp.rb.transform != handR &&
// bp.rb.transform != footL && bp.rb.transform != footR)
// sensor.AddObservation(RagdollHelpers.GetJointRotation(bp.joint));
// sensor.AddObservation(bp.currentXNormalizedRot);
// sensor.AddObservation(bp.currentYNormalizedRot);
// sensor.AddObservation(bp.currentZNormalizedRot);
// /// <summary>
// /// Add relevant information on each body part to observations.
// /// </summary>
// public void CollectObservationBodyPart(BodyPart bp, VectorSensor sensor)
// {
// var rb = bp.rb;
// sensor.AddObservation(bp.groundContact.touchingGround ? 1 : 0); // Is this bp touching the ground
// sensor.AddObservation(rb.velocity);
// sensor.AddObservation(rb.angularVelocity);
// var localPosRelToHips = hips.InverseTransformPoint(rb.position);
// sensor.AddObservation(localPosRelToHips);
//
// if (bp.rb.transform != hips && bp.rb.transform != handL && bp.rb.transform != handR &&
// bp.rb.transform != footL && bp.rb.transform != footR && bp.rb.transform != head)
// {
// sensor.AddObservation(bp.currentXNormalizedRot);
// sensor.AddObservation(bp.currentYNormalizedRot);
// sensor.AddObservation(bp.currentZNormalizedRot);
// sensor.AddObservation(bp.currentStrength / m_JdController.maxJointForceLimit);
// }
// }
// m_JdController.GetCurrentJointForces();
// Update pos to target
// m_WalkDir = target.position - hips.position;
// m_WalkDir = target.position - m_OrientationCube.transform.position;
// print($"fromTo: {Quaternion.FromToRotation(m_OrientationCube.transform.forward, hips.forward)} rotDelta {RagdollHelpers.GetRotationDelta(m_WalkDirLookRot, hips.rotation)}");
// sensor.AddObservation(RagdollHelpers.GetRotationDelta(m_WalkDirLookRot, hips.rotation));
// sensor.AddObservation(Quaternion.FromToRotation(m_OrientationCube.transform.forward, hips.forward));
// sensor.AddObservation(Quaternion.FromToRotation(m_OrientationCube.transform.forward, head.forward));
// sensor.AddObservation(RagdollHelpers.GetRotationDelta(m_WalkDirLookRot, chest.rotation));
// sensor.AddObservation(RagdollHelpers.GetRotationDelta(m_WalkDirLookRot, head.rotation));
// m_TargetDirMatrix = Matrix4x4.TRS(Vector3.zero, m_LookRotation, Vector3.one);
// //HIP RAYCAST FOR HEIGHT
// RaycastHit hit;
// if (Physics.Raycast(hips.position, Vector3.down, out hit, 10.0f))
// {
// sensor.AddObservation(hit.distance);
// }
// else
// sensor.AddObservation(10.0f);
// //ORIENTATION MATRIX
// Vector3 worldPosMatrixPos = hips.position;
// worldPosMatrixPos.y = .5f;
// m_worldPosMatrix = Matrix4x4.TRS(worldPosMatrixPos, Quaternion.identity, Vector3.one);
// sensor.AddObservation(m_WalkDir.normalized);
//HIP POS REL TO MATRIX
// sensor.AddObservation(hips.position - worldPosMatrixPos);
// sensor.AddObservation(hips.position - m_OrientationCube.transform.position);
// sensor.AddObservation(m_JdController.bodyPartsDict[hips].rb.position);
// sensor.AddObservation(hips.forward);
// sensor.AddObservation(hips.up);
//// print(m_OrientationCube.transform.rotation.eulerAngles);
//// Debug.DrawRay(m_OrientationCube.transform.position, m_OrientationCube.transform.InverseTransformVector(m_JdController.bodyPartsDict[hips].rb.velocity), Color.green,Time.fixedDeltaTime * 5);
// AddReward(
//// runForwardTowardsTargetReward
//// facingReward * velReward //max reward is moving towards while facing otherwise it is a penalty
//// +0.02f * Vector3.Dot(m_WalkDir.normalized, m_JdController.bodyPartsDict[hips].rb.velocity)
//// + 0.02f * Vector3.Dot(m_OrientationCube.transform.forward,Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity,5))
// +0.01f * Vector3.Dot(m_OrientationCube.transform.forward,
// Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity, 3))
// + 0.01f * Vector3.Dot(m_OrientationCube.transform.forward, hips.forward)
//
//// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, chest.rotation) //reward looking at
//// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) //reward looking at
//// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation) //reward looking at
//// + 0.015f * (Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) - 1) *
//// .5f //penalize not looking at
//// + 0.015f * (Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation) - 1) *
//// .5f //penalize not looking at
//
// + 0.005f * (head.position.y - shinL.position.y)
// + 0.005f * (head.position.y - shinR.position.y)
//// + 0.01f * (head.position.y - shinL.position.y)
//// + 0.01f * (head.position.y - shinR.position.y)
//// - 0.005f * Mathf.Clamp(m_JdController.bodyPartsDict[handL].rb.velocity.magnitude,
//// 6, 9999)
//// - 0.005f * Mathf.Clamp(m_JdController.bodyPartsDict[handR].rb.velocity.magnitude,
//// 6, 9999)
//// + 0.02f * (head.position.y - hips.position.y)
//// - 0.01f * Vector3.Distance(m_JdController.bodyPartsDict[head].rb.velocity,
//// m_JdController.bodyPartsDict[hips].rb.velocity)
// );
}
public override void OnActionReceived(float[] vectorAction)

bpDict[forearmL].SetJointStrength(vectorAction[++i]);
bpDict[armR].SetJointStrength(vectorAction[++i]);
bpDict[forearmR].SetJointStrength(vectorAction[++i]);
// print(Vector3.Dot(m_OrientationCube.transform.forward,
// Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity, 3)));
// print((Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) - 1) * .5f);
// print(Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation));
// print(Vector3.Dot(m_OrientationCube.transform.forward, hips.transform.forward));
}
void UpdateOrientationCube()

m_WalkDir.y = 0;
// m_WalkDir = walkDirWorldspace;
m_WalkDirLookRot = Quaternion.LookRotation(m_WalkDir);
m_WalkDir.y = 0; //flatten dir on the y
m_WalkDirLookRot = Quaternion.LookRotation(m_WalkDir); //get our look rot to the target
Vector3 oCubePos = hips.position;
// oCubePos.y = -.45f;
m_OrientationCube.transform.position = oCubePos;
m_OrientationCube.transform.position = hips.position;
cubeRotation = m_OrientationCube.transform.rotation;
hipsRotation = hips.rotation;
directionIndicator.position = new Vector3(hips.position.x, directionIndicator.position.y, hips.position.z);
directionIndicator.rotation = m_WalkDirLookRot;
void FixedUpdate()
{

}
}
}
//reward looking at
// float facingReward = + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation)
// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation);
// print($"FacingRewardDot {facingReward}");
// float velReward = +0.02f * Vector3.Dot(m_OrientationCube.transform.forward,m_OrientationCube.transform.InverseTransformVector(m_JdController.bodyPartsDict[hips].rb.velocity));
// print($"VelRewardDot {velReward}");
// float velReward = +0.02f * Vector3.Dot(m_WalkDir.normalized, m_JdController.bodyPartsDict[hips].rb.velocity);
// //Multiplying these amplifies the reward.
// float facingReward = + 0.1f * Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation)
// + 0.1f * Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation);
// float velReward = +0.2f * Vector3.Dot(m_OrientationCube.transform.forward,m_JdController.bodyPartsDict[hips].rb.velocity); //because we are observing in local space???
// float runForwardTowardsTargetReward = facingReward * Mathf.Clamp(velReward, 0, 15);
// print(Quaternion.Angle(hips.transform.rotation, thighL.transform.rotation));
// print($"Combined {runForwardTowardsTargetReward}");
// float runBackwardsTowardsTargetReward = facingReward * Mathf.Clamp(velReward, -1, 0);
// d. Discourage head movement.
// runForwardTowardsTargetReward
// facingReward * velReward //max reward is moving towards while facing otherwise it is a penalty
// +0.02f * Vector3.Dot(m_WalkDir.normalized, m_JdController.bodyPartsDict[hips].rb.velocity)
// + 0.02f * Vector3.Dot(m_OrientationCube.transform.forward,Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity,5))
Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity, 999))
// + 0.01f * Vector3.Dot(m_OrientationCube.transform.forward, hips.forward)
Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity, maximumWalkingSpeed))
// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, chest.rotation) //reward looking at
// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) //reward looking at
// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation) //reward looking at
// + 0.015f * (Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) - 1) *
// .5f //penalize not looking at
// + 0.015f * (Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation) - 1) *
// .5f //penalize not looking at
// + 0.005f * (head.position.y - shinL.position.y)
// + 0.005f * (head.position.y - shinR.position.y)
// + 0.01f * (head.position.y - shinL.position.y)
// + 0.01f * (head.position.y - shinR.position.y)
// - 0.005f * Mathf.Clamp(m_JdController.bodyPartsDict[handL].rb.velocity.magnitude,
// 6, 9999)
// - 0.005f * Mathf.Clamp(m_JdController.bodyPartsDict[handR].rb.velocity.magnitude,
// 6, 9999)
// + 0.02f * (head.position.y - hips.position.y)
// - 0.01f * Vector3.Distance(m_JdController.bodyPartsDict[head].rb.velocity,
// m_JdController.bodyPartsDict[hips].rb.velocity)
// var handLVel = m_JdController.bodyPartsDict[handL].rb.velocity.magnitude;
// var handRVel = m_JdController.bodyPartsDict[handR].rb.velocity.magnitude;
// if (handLVel > 6)
// {
// AddReward(-0.005f * handLVel);
// }
// if (handRVel > 6)
// {
// AddReward(-0.005f * handRVel);
// }
// //SUNDAY VERSION
// AddReward(
//// runForwardTowardsTargetReward
//// facingReward * velReward //max reward is moving towards while facing otherwise it is a penalty
//// +0.02f * Vector3.Dot(m_WalkDir.normalized, m_JdController.bodyPartsDict[hips].rb.velocity)
//// + 0.02f * Vector3.Dot(m_OrientationCube.transform.forward,Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity,5))
// + 0.01f * Vector3.Dot(m_OrientationCube.transform.forward,Vector3.ClampMagnitude(m_JdController.bodyPartsDict[hips].rb.velocity,3))
//// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) //reward looking at
//// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation) //reward looking at
// + 0.015f * (Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation) - 1) * .5f //penalize not looking at
// + 0.015f * (Quaternion.Dot(m_OrientationCube.transform.rotation, head.rotation) - 1) * .5f //penalize not looking at
//
//
//
//// + 0.02f * (head.position.y - hips.position.y)
//// - 0.01f * Vector3.Distance(m_JdController.bodyPartsDict[head].rb.velocity,
//// m_JdController.bodyPartsDict[hips].rb.velocity)
// );
// // Set reward for this step according to mixture of the following elements.
// // a. Velocity alignment with goal direction.
// // b. Rotation alignment with goal direction.
// // c. Encourage head height.
// // d. Discourage head movement.
// m_WalkDir = target.position - m_OrientationCube.transform.position;
// AddReward(
// +0.03f * Vector3.Dot(m_WalkDir.normalized, m_JdController.bodyPartsDict[hips].rb.velocity)
// + 0.01f * Quaternion.Dot(m_OrientationCube.transform.rotation, hips.rotation)
// + 0.02f * (head.position.y - hips.position.y)
// - 0.01f * Vector3.Distance(m_JdController.bodyPartsDict[head].rb.velocity,
// m_JdController.bodyPartsDict[hips].rb.velocity)
// );
// m_WalkDir = target.position - m_JdController.bodyPartsDict[hips].rb.position;
// AddReward(
// +0.03f * Vector3.Dot(m_WalkDir.normalized, m_JdController.bodyPartsDict[hips].rb.velocity)
// + 0.01f * Vector3.Dot(m_WalkDir.normalized, hips.forward)
// + 0.02f * (head.position.y - hips.position.y)
// - 0.01f * Vector3.Distance(m_JdController.bodyPartsDict[head].rb.velocity,
// m_JdController.bodyPartsDict[hips].rb.velocity)
// );
}
/// <summary>

target.position = newTargetPos + ground.position;
}
// print("OnEpisodeBegin");
// if (m_WalkDir != Vector3.zero)
// {
// transform.rotation = Quaternion.LookRotation(m_WalkDir);
// }
//Random start rotation
// transform.Rotate(Vector3.up, Random.Range(0.0f, 360.0f));
if (detectTargets && !targetIsStatic)
{

public void SetResetParameters()
{
SetTorsoMass();
}
private void OnDrawGizmosSelected()
{
if (showOrientationCubeGizmo && Application.isPlaying)
{
Gizmos.color = Color.green;
Gizmos.matrix = m_OrientationCube.transform.localToWorldMatrix;
Gizmos.DrawWireCube(Vector3.zero, m_OrientationCube.transform.localScale);
Gizmos.DrawRay(Vector3.zero, Vector3.forward);
}
}
}

5
Project/Assets/ML-Agents/Examples/WallJump/Materials/TransparentWall.mat
查看文件


Material:
serializedVersion: 6
m_ObjectHideFlags: 0
m_PrefabParentObject: {fileID: 0}
m_PrefabInternal: {fileID: 0}
m_CorrespondingSourceObject: {fileID: 0}
m_PrefabInstance: {fileID: 0}
m_PrefabAsset: {fileID: 0}
m_Name: TransparentWall
m_Shader: {fileID: 46, guid: 0000000000000000f000000000000000, type: 0}
m_ShaderKeywords: _ALPHABLEND_ON

撰写 预览
正在加载...
取消
保存