Environments – Mobile Robotics
Navigation and locomotion configuration and contracts target Isaac Sim 6.1.0 with Isaac Lab 3.0.0; hardware readiness is not claimed.
Aerial (_aerial)
Template environment for aerial mobile robots. Configure via
env.robot=<aerial_robot>.
Readiness: simulator-only. No learned-policy, real-data or hardware evidence for aerial platforms is recorded in the capability ledger (
docs/data/capabilities.toml); every lane there is still atpresent.
| Episode Length | 10.0s (250 steps) |
| Reward Terms | 1 |
| Default Robot | Ingenuity |
Compatible Robots
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – |
Ground (_ground)
Template environment for ground mobile robots. Configure via
env.robot=<ground_robot>.
| Episode Length | 10.0s (250 steps) |
| Reward Terms | 1 |
| Default Robot | Cadre |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – |
Orbital (_orbital)
Template environment for orbital mobile robots. Configure via
env.robot=<orbital_robot>.
| Episode Length | 10.0s (250 steps) |
| Reward Terms | 2 |
| Default Robot | Cubesat |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_fuel_consumption | Linear | -1 | – |
Camera depth range. Orbital cameras use
camera_clipping_range = (0.01, 100.0) m; rendezvous uses 50 m,
orbital_evasion 150 m, and landing and moonfall 400 m. Geometry beyond the
far plane is not rendered. Override with env.camera_clipping_range=[near,far].
Aerial Navigation (aerial_navigation)
Aerial navigation to a dynamic waypoint with terrain-clearance tracking
Readiness: simulator-only. No learned-policy, real-data or hardware evidence for aerial platforms is recorded in the capability ledger (
docs/data/capabilities.toml); every lane there is still atpresent.
| Episode Length | 60.0s (1500 steps) |
| Reward Terms | 7 |
| Default Robot | Ingenuity |
Compatible Robots
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| reward_altitude_tracking | HyperbolicTracking | 4 | 1 | |
| reward_waypoint_approach | Hyperbolic | 16 | 2 | |
| penalty_tilt_angle | OffsetLinear | -2 | – | |
| reward_terrain_clearance | HyperbolicBarrier | 8 | 0.5 | |
| penalty_energy | Linear | -0.5 | – | |
| reward_waypoint_reached | Threshold | 32 | – |
Success signal: return only. Evaluation reports the return, not a success rate.
Beam Transport (beam_transport)
Two-robot collaborative transport of a rigid beam payload to a target point
Readiness: simulator-only. Earlier baseline results are stale, and training readiness is not established.
Two Spot quadrupeds carry one beam to
a target on MoonSurface terrain,
driven by one centralized policy. The beam is kinematically mounted to the pair;
set env.beam_kinematic_mount_enabled=false for a free beam.
| Episode Length | 30.0s (750 steps) |
| Reward Terms | 15 |
| Default Robot | Spot |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| reward_beam_position | Gaussian | 16 | 1.5 | |
| reward_beam_midpoint_alignment | Gaussian | 10 | 0.25 | |
| reward_robot_support_slots | Gaussian | 12 | 0.2 | |
| reward_beam_progress | Scaled | 8 | – | |
| reward_attachment_balance | Gaussian | 4 | 0.15 | |
| reward_success | Linear | 24 | – | |
| penalty_beam_tilt | Linear | -4 | – | |
| penalty_beam_drop | Linear | -16 | – | |
| penalty_beam_speed | Linear | -2 | – | |
| penalty_joint_torque | Linear | -0.000025 | – | |
| penalty_joint_acceleration | Linear | -0.00000025 | – | |
| penalty_undesired_lin_vel_z | Linear | -0.5 | – | |
| penalty_undesired_ang_vel_xy | Linear | -0.1 | – | |
| penalty_gravity_rotation_alignment | Linear | -2 | – |
Success. The beam stays within 0.20 m of the target, aligned with both robots and moving slowly, for 8 consecutive control steps.
Success signal: episode info. Evaluation reports a success rate and the return.
Flight (flight)
Generic powered aerial flight profile with takeoff, transfer, and final landing
A rotorcraft takes off on Mars, flies to a landing pad and lands within 90 s.
Set env.landing_only=true to start in the final descent.
| Episode Length | 90.0s (2250 steps) |
| Reward Terms | 8 |
| Default Robot | Ingenuity |
Compatible Robots
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| reward_waypoint_approach | Hyperbolic | 12 | 4 | |
| reward_altitude_tracking | HyperbolicTracking | 6 | 1 | |
| reward_waypoint_reached | Threshold | 20 | – | |
| penalty_tilt_angle | OffsetLinear | -2 | – | |
| reward_terrain_clearance | HyperbolicBarrier | 6 | 0.8 | |
| penalty_energy | Linear | -0.6 | – | |
| reward_mission_progress | Linear | 60 | – |
Only a crash (low terrain clearance or excessive tilt) terminates. Reaching the
pad sets success; the episode then runs to the time limit.
Formation Following (formation_following)
Multi-robot formation tracking behind a moving formation center
Readiness: simulator-only. Earlier baseline results are stale, and training readiness is not established.
Three Cadre rovers hold triangular
formation slots around a drifting centre, driven by one centralized policy. With
a ROS node, the centre follows the formation_center TF frame.
| Episode Length | 60.0s (1500 steps) |
| Reward Terms | 9 |
| Default Robot | Cadre |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_formation_tracking | Linear | -1 | – | |
| reward_formation_progress | Scaled | 4 | – | |
| reward_formation_velocity | Linear | 2 | – | |
| reward_point_towards_target | Linear | 0.5 | – | |
| reward_formation_precision | Linear | 4 | – | |
| reward_in_zone | Linear | 0 | – | |
| reward_formation_orientation | Linear | 4 | – | |
| reward_action_rate_in_formation | Linear | 32 | – |
Success. All rovers stay within 0.20 m and 20° of their slots for 8 consecutive control steps.
Success signal: episode info. Evaluation reports a success rate and the return.
Formation Following Decentralized (formation_following_decentralized)
Single-rover policy view for decentralized formation following
| Episode Length | 60.0s (1500 steps) |
| Reward Terms | 9 |
| Default Robot | Cadre |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_formation_tracking | Linear | -1 | – | |
| reward_formation_progress | Scaled | 4 | – | |
| reward_formation_velocity | Linear | 2 | – | |
| reward_point_towards_target | Linear | 0.5 | – | |
| reward_formation_precision | Linear | 4 | – | |
| reward_in_zone | Linear | 0 | – | |
| reward_formation_orientation | Linear | 4 | – | |
| reward_action_rate_in_formation | Linear | 32 | – |
Formation Following Orbital (formation_following_orbital)
Orbital formation tracking in microgravity
| Episode Length | 60.0s (600 steps) |
| Reward Terms | 7 |
| Default Robot | Cubesat |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -8 | – | |
| penalty_fuel_consumption | Linear | 0 | – | |
| penalty_action_magnitude | Linear | -8 | – | |
| penalty_formation_tracking | Linear | -2 | – | |
| reward_formation_precision | Linear | 16 | – | |
| reward_formation_orientation | Linear | 48 | – | |
| reward_action_rate_in_formation | Linear | 48 | – |
Slot assignment. With randomize_formation_assignment = false, environment
i always takes formation slot i % N (N formation positions), including
after partial resets; with it enabled, each reset draws a slot at random.
Landing (landing)
Landing of spacecraft on planetary surfaces with varying terrain and obstacles
| Episode Length | 40.0s (1000 steps) |
| Reward Terms | 11 |
| Default Robot | Peregrine Lander |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_fuel_consumption | Linear | -1 | – | |
| penalty_angular_velocity | Linear | -0.25 | – | |
| penalty_gravity_rotation_alignment | Linear | -1 | – | |
| penalty_horizontal_linear_velocity | Linear | -0.1 | – | |
| reward_vertical_linear_velocity | Hyperbolic | 8 | 1 | |
| reward_landing_angle | Linear | 8 | – | |
| reward_landing_velocity | Linear | 16 | – | |
| reward_landing_fuel | Linear | 4 | – | |
| penalty_crash | Linear | -32 | – | |
| penalty_below_target | Linear | -16 | – |
Success signal: return only. Evaluation reports the return, not a success rate.
Event camera (opt-in; disabled by default). Set
env.enable_event_camera_onboard=true to add the onboard event camera.
Locomotion Velocity Tracking (locomotion_velocity_tracking)
Locomotion with legged robots and humanoids while tracking desired velocity commands
Readiness: simulator-only. No learned-policy, real-data or hardware evidence for legged or humanoid platforms is recorded in the capability ledger (
docs/data/capabilities.toml); every lane there is still atpresent.
| Episode Length | 20.0s (500 steps) |
| Reward Terms | 12 |
| Default Robot | Spot |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cassie | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped | Humanoid21 | Humanoid28 | Unitree H1 | Unitree G1
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| reward_cmd_lin_vel_xy | Linear | 4 | – | |
| reward_cmd_ang_vel_z | Linear | 2 | – | |
| penalty_undesired_lin_vel_z | Linear | -0.5 | – | |
| penalty_undesired_ang_vel_xy | Linear | -0.1 | – | |
| penalty_joint_torque | Linear | -0.000025 | – | |
| penalty_joint_acceleration | Linear | -0.00000025 | – | |
| penalty_undesired_robot_contacts | Threshold | -2 | – | |
| penalty_gravity_rotation_alignment | Linear | -2 | – | |
| reward_feet_air_time | Linear | 0.75 | – | |
| reward_quadruped_trot | Linear | 1 | – | |
| penalty_foot_slip | Linear | -0.5 | – |
Success signal: return only. Evaluation reports the return, not a success rate.
Locomotion Waypoint Navigation (locomotion_waypoint_navigation)
Navigation to a dynamic waypoint with legged robots and humanoids
Readiness: simulator-only. No learned-policy, real-data or hardware evidence for legged or humanoid platforms is recorded in the capability ledger (
docs/data/capabilities.toml); every lane there is still atpresent.
| Episode Length | 60.0s (1500 steps) |
| Reward Terms | 13 |
| Default Robot | Spot |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cassie | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped | Humanoid21 | Humanoid28 | Unitree H1 | Unitree G1
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_position_tracking | Linear | -1 | – | |
| reward_point_towards_target | Linear | 1 | – | |
| reward_position_tracking_precision | Linear | 4 | – | |
| reward_orientation_tracking | Linear | 8 | – | |
| reward_action_rate_at_target | Linear | 16 | – | |
| penalty_joint_torque | Linear | -0.000025 | – | |
| penalty_joint_acceleration | Linear | -0.00000025 | – | |
| penalty_undesired_robot_contacts | Threshold | -2 | – | |
| penalty_undesired_lin_vel_z | Linear | -0.5 | – | |
| penalty_undesired_ang_vel_xy | Linear | -0.1 | – | |
| penalty_gravity_rotation_alignment | Linear | -2 | – | |
| reward_feet_air_time | Linear | 0.5 | – |
Non-foot contact or a fall terminates; the time limit is a truncation.
Success signal: return only. Evaluation reports the return, not a success rate.
Moonfall (moonfall)
Heavy-weight lunar descent with deployment stage and multi-stage landing phases
| Episode Length | 70.0s (1750 steps) |
| Reward Terms | 12 |
| Default Robot | Peregrine Lander |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_fuel_consumption | Linear | -1 | – | |
| penalty_angular_velocity | Linear | -0.25 | – | |
| penalty_gravity_rotation_alignment | Linear | -1 | – | |
| penalty_horizontal_linear_velocity | Linear | -0.1 | – | |
| reward_waypoint_progress | Hyperbolic | 4 | 4 | |
| reward_vertical_linear_velocity | Hyperbolic | 8 | 1 | |
| reward_landing_angle | Linear | 8 | – | |
| reward_landing_velocity | Linear | 16 | – | |
| reward_landing_fuel | Linear | 4 | – | |
| penalty_crash | Linear | -32 | – | |
| penalty_below_target | Linear | -16 | – |
Event camera (opt-in; disabled by default). Set
env.enable_event_camera_onboard=true to add the onboard event camera.
Orbital Evasion (orbital_evasion)
Navigation of spacecraft in microgravity while avoiding obstacles
| Episode Length | 30.0s (750 steps) |
| Reward Terms | 7 |
| Default Robot | Cubesat |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_fuel_consumption | Linear | -1 | – | |
| penalty_angular_velocity | Linear | -0.25 | – | |
| reward_obstacle_clearance | HyperbolicBarrier | 4 | 2 | |
| penalty_distance_robot_to_target | Linear | -0.32 | – | |
| penalty_out_of_bounds | Linear | -16 | – | |
| reward_target_approach | Hyperbolic | 8 | 5 |
Termination semantics. max_target_distance drives the
penalty_out_of_bounds reward and does not set terminated. Entering an
asteroid’s keep-out sphere terminates; the time limit is reported as
truncated.
Success signal: return only. Evaluation reports the return, not a success rate.
Orbital Waypoint Navigation (orbital_waypoint_navigation)
Navigation to a dynamic waypoint in orbital microgravity
| Episode Length | 30.0s (300 steps) |
| Reward Terms | 9 |
| Default Robot | Satellite Mockup |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | LogCosh | -4 | – | |
| penalty_fuel_consumption | Linear | 0 | – | |
| penalty_action_magnitude | LogCosh | -1 | – | |
| penalty_angular_velocity | LogCosh | -2 | – | |
| penalty_position_distance | Linear | -1 | – | |
| penalty_velocity_at_target | LogCosh | -4 | – | |
| reward_position_approach | Hyperbolic | 4 | 2 | |
| reward_position_precision | Scaled | 8 | – | |
| reward_smooth_station_keeping | Scaled | 8 | – |
Success signal: return only. Evaluation reports the return, not a success rate.
Rendezvous (rendezvous)
Maneuvering of spacecraft in microgravity to rendezvous with an uncooperative target
| Episode Length | 25.0s (625 steps) |
| Reward Terms | 7 |
| Default Robot | Cubesat |
Compatible Robots
Floating Platform | Int Ball1 | Int Ball2 | Apollo Lander | Peregrine Lander | Vikram Lander | Resilience Lander | Random Lander | Iss | Gateway | Cubesat | Satellite Mockup | Venus Express | Starship | Super Heavy
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_fuel_consumption | Linear | -8 | – | |
| penalty_angular_velocity | Linear | -0.05 | – | |
| penalty_distance_robot_to_target | Linear | -16 | – | |
| penalty_too_far | Linear | -16 | – | |
| reward_precision_position | Gaussian | 128 | 0.025 | |
| reward_precision_orientation | Linear | 128 | – |
Termination semantics. max_target_distance drives the
penalty_too_far reward. Exceeding it leaves terminated false so the agent
can recover; only the time limit sets truncated.
Success signal: return only. Evaluation reports the return, not a success rate.
Terrain Landscaping (terrain_landscaping)
Terrain landscaping with a ground mobile robot reshaping a particle bed
Readiness: blocked. No learned policy exists, Dreamer with
num_envs > 1and TD-MPC2 are rejected fail-closed, and theraph-hardwarelane of the capability ledger has no evidence.
A RaphRover with a RaphShovel reshapes a regolith particle bed toward a
per-episode target heightmap. The action is
[rover_linear_velocity, rover_angular_velocity, shovel_linear_velocity].
srb agent teleop -e terrain_landscaping env.num_envs=1
| Episode Length | 60.0s (600 steps) |
| Reward Terms | 0 |
| Default Robot | Raph Rover |
Compatible Robots
The policy observes current and target heightmaps, the rover pose and velocity,
but not the shovel extension, so TD-MPC2 is disabled. The reward is
1 / (1 + mae / 0.02); episodes end only at the time limit. See Terrain Landscaping Training Readiness.
Terrain Landscaping Crater (terrain_landscaping_crater)
Separate deterministic baseline: fill one shallow crater from a nearby regolith pile
Readiness: blocked. No learned policy exists, Dreamer with
num_envs > 1and TD-MPC2 are rejected fail-closed, and theraph-hardwarelane of the capability ledger has no evidence.
A separate task, not a curriculum stage of terrain_landscaping: level a bed
with one crater and one regolith pile from a fixed rover pose. Actions and
observations match terrain_landscaping.
srb agent teleop -e terrain_landscaping_crater env.num_envs=1
srb agent train --headless --algo skrl_ppo -e terrain_landscaping_crater
| Episode Length | 30.0s (300 steps) |
| Reward Terms | 0 |
| Default Robot | Raph Rover |
Compatible Robots
Crater and pile geometry are overridable under env.*. Dreamer runs only with
env.num_envs=1, TD-MPC2 is disabled, and particle physics needs an NVIDIA
GPU. See Terrain Landscaping Training Readiness.
Terrain Landscaping Mound (terrain_landscaping_mound)
Separate deterministic baseline: level one regolith mound on a flat bed, graded by excess volume
Readiness: blocked. No learned policy exists, Dreamer with
num_envs > 1and TD-MPC2 are rejected fail-closed, and theraph-hardwarelane of the capability ledger has no evidence.
| Episode Length | 30.0s (300 steps) |
| Reward Terms | 0 |
| Default Robot | Raph Rover |
Compatible Robots
Traversal (traversal)
Straight-line path following at a target velocity
| Episode Length | 120.0s (3000 steps) |
| Reward Terms | 5 |
| Default Robot | Nifty |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.05 | – | |
| penalty_lateral_pos_deviation | Linear | -1 | – | |
| reward_vel_progress | Linear | 8 | – | |
| reward_action_rate_at_target | Linear | 32 | – | |
| penalty_rollover | Linear | -16 | – |
Termination semantics. max_tilt_rad drives the penalty_rollover
reward. Exceeding the tilt threshold leaves terminated false so the rover
can recover; the time limit is reported as truncated.
Success signal: return only. Evaluation reports the return, not a success rate.
Velocity Tracking (velocity_tracking)
Basic tracking of desired velocity commands
| Episode Length | 20.0s (500 steps) |
| Reward Terms | 5 |
| Default Robot | Cadre |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| reward_cmd_lin_vel_xy | Linear | 4 | – | |
| reward_cmd_ang_vel_z | Linear | 2 | – | |
| penalty_undesired_lin_vel_z | Linear | -0.5 | – | |
| penalty_undesired_ang_vel_xy | Linear | -0.1 | – |
Success signal: return only. Evaluation reports the return, not a success rate.
Event camera (opt-in; disabled by default). Set
env.enable_event_camera_front=true to add the front event camera.
Waypoint Navigation (waypoint_navigation)
Navigation to a dynamic waypoint
| Episode Length | 60.0s (1500 steps) |
| Reward Terms | 6 |
| Default Robot | Cadre |
Compatible Robots
Anymal C | Anymal D | Random Anymal Quadruped | Cadre | Cassie | Husky | Leo Rover | Mars Rover | Nifty | Open Source Rover | Perseverance | Pragyan | Raph Rover | Spot | Unitree A1 | Unitree Go1 | Unitree Go2 | Random Unitree Quadruped
Reward Breakdown
| Term | Type | Weight | Scale | Notes |
|---|---|---|---|---|
| penalty_action_rate | Linear | -0.1 | – | |
| penalty_position_tracking | Linear | -1 | – | |
| reward_point_towards_target | Linear | 1 | – | |
| reward_position_tracking_precision | Linear | 4 | – | |
| reward_orientation_tracking | Linear | 8 | – | |
| reward_action_rate_at_target | Linear | 16 | – |
Success signal: return only. Evaluation reports the return, not a success rate.
Event camera (opt-in; disabled by default). Set
env.enable_event_camera_front=true to add the front event camera.