Adds DisplayPort cable insertion envs

[shauryadNv]

Description

Added envs to train and run inference for the new task of DisplayPort cable insertion task with the Flexiv Rizon 4s robot. Supports multiple env variants based on policy design choices such as operating in joint space vs task space and the observation space used.
Added documentation for a tutorial on training a DisplayPort cable insertion policy with Flexiv Rizon 4s.

Type of change

• New feature (non-breaking change which adds functionality)
• Documentation update

Checklist

• I have read and understood the contribution guidelines
• I have run the pre-commit checks with ./isaaclab.sh --format
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• I have updated the changelog and the corresponding version in the extension's config/extension.toml file
• I have added my name to the CONTRIBUTORS.md or my name already exists there

[greptile-apps]

Greptile Summary

This PR adds DisplayPort cable insertion environments and tooling. The main changes are:

• New DisplayPort plug/socket assets and diagnostic scripts.
• New basic, joint-space, task-space, and ROS inference environment configs.
• New reset, grasp, observation, reward, termination, action-delay, and success-logging helpers.
• Gym registrations for the new DisplayPort task variants.

Confidence Score: 4/5

The task-space training path needs a config fix before merging.

• The new environments are mostly additive and the main import and reset wiring is consistent.
• The task-space reset curriculum is disabled by its own default values.
• That can make task-space training run without the seeded insertion starts described by the config.

source/isaaclab_tasks/isaaclab_tasks/contrib/deploy/cable_insertion/config/displayport_rizon_4s/task_space_env_cfg.py

Important Files Changed

Filename	Overview
source/isaaclab_tasks/isaaclab_tasks/contrib/deploy/cable_insertion/config/displayport_rizon_4s/task_space_env_cfg.py	Defines the task-space DisplayPort insertion environment; the at-goal curriculum is configured but disabled.
source/isaaclab_tasks/isaaclab_tasks/contrib/deploy/cable_insertion/config/displayport_rizon_4s/joint_pos_env_cfg.py	Defines the joint-position DisplayPort insertion environment and wires robot, reset, action, and termination settings.
source/isaaclab_tasks/isaaclab_tasks/contrib/deploy/mdp/events.py	Adds generic object grasp reset logic and plug-at-goal curriculum reset logic.
source/isaaclab_tasks/isaaclab_tasks/contrib/deploy/mdp/terminations.py	Adds plug drop and plug orientation termination terms for the insertion environments.
source/isaaclab_tasks/isaaclab_tasks/contrib/deploy/cable_insertion/insertion_env.py	Adds success metric logging for DisplayPort insertion rollouts.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
  A[DisplayPort Gym task id] --> B[DisplayportInsertionEnv]
  B --> C[Environment config]
  C --> D[Reset events]
  D --> E[reset_scene_to_default]
  E --> F[randomize_socket_pose]
  F --> G[reset_plug_at_goal_curriculum]
  G --> H[set_robot_to_object_grasp_pose]
  C --> I[Policy observations and actions]
  C --> J[Rewards and terminations]
  B --> K[Success metric logging]

Loading

%%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%%
flowchart TD
  A[DisplayPort Gym task id] --> B[DisplayportInsertionEnv]
  B --> C[Environment config]
  C --> D[Reset events]
  D --> E[reset_scene_to_default]
  E --> F[randomize_socket_pose]
  F --> G[reset_plug_at_goal_curriculum]
  G --> H[set_robot_to_object_grasp_pose]
  C --> I[Policy observations and actions]
  C --> J[Rewards and terminations]
  B --> K[Success metric logging]

Loading

_{Reviews (1): Last reviewed commit: "Relocate DisplayPort cable_insertion und..." | Re-trigger Greptile}

[greptile-apps]

At-Goal Curriculum Disabled

The task-space config documents and wires an at-goal curriculum, but both probabilities are 0.0. reset_plug_at_goal_curriculum only enters the at-goal branch when the current probability is positive, so every reset uses the normal approach-pose randomization and the task-space policy never receives the seeded insertion starts this config describes.

Suggested change

	"at_goal_prob": 0.0,
	"at_goal_prob_final": 0.0,
	"at_goal_prob": 0.8,
	"at_goal_prob_final": 0.0,