Skip to main content
env.json is the single source of truth for a mission. This page documents every field. Coordinates are world-space, and forward is −X.

​
Top level

KeyTypeMeaning
namestringMission name (used in fine-tune prompts).
robotstringgo1 (default) or g1.
spawn[x, y, z]Robot start position.
sceneobjectStatic world: objects and zones.
phasesarrayOrdered sub-goals, executed in sequence.
vla_finetuneobjectPrompt template for exported training rows.

​
scene

"scene": {
  "objects": [
    {"type": "box",    "tag": "rubble", "position": [-1.35, 0.20, 0.08],
     "size": [0.18, 0.18, 0.08]},
    {"type": "marker", "tag": "victim", "position": [-2.80, 0.0, 0.02],
     "size": [0.12, 0.12, 0.02], "rgba": [1.0, 0.2, 0.2, 1.0]}
  ],
  "zones": [
    {"name": "spawn",            "aabb": [[-0.5,-0.8,0],[ 0.5,0.8,1]]},
    {"name": "debris_perimeter", "aabb": [[-1.2,-0.9,0],[-0.8,0.9,1]]}
  ]
}
Objects
FieldMeaning
typebox (solid, collidable) or marker (visual-only thin plate).
tagLabel referenced by rewards/predicates (e.g. rubble, victim). Tags need not be unique.
position[x, y, z] center, world coords.
size[sx, sy, sz] half-extents.
rgbaOptional color [r, g, b, a] (markers).
Zones
FieldMeaning
nameZone name, referenced by predicates and distance_to_zone.
aabbAxis-aligned box [[min_x,min_y,min_z],[max_x,max_y,max_z]].

​
phases

Phases run in order. The mission advances when a phase’s success_when fires, and ends early if any fail_when fires or max_ticks is exceeded. 
{
  "name": "approach",
  "goal_prompt": "walk forward 1.0 meters and reach the edge of the debris field",
  "success_when": {"enter_zone": "debris_perimeter"},
  "fail_when":    {"flipped": true},
  "reward": {
    "step_cost": -0.05,
    "distance_to_zone": {"zone": "debris_perimeter", "weight": 0.4},
    "forward_distance_gain": 0.2,
    "fall_penalty": -2.0,
    "phase_success_bonus": 2.0
  },
  "max_ticks": 25
}
FieldMeaning
namePhase identifier.
goal_promptNatural-language goal. Drives the scripted driver and is the prompt fed to a policy/VLA for this phase.
success_whenPredicate that completes the phase.
fail_whenPredicate that fails the phase (usually {"flipped": true}).
rewardReward-shaping terms (below).
max_ticksPhase timeout.

​
Predicates

Used by both success_when and fail_when:
PredicateFires when
{"enter_zone": "<name>"}Robot enters the named zone.
{"exit_zone": "<name>"}Robot leaves the named zone.
{"near_object": {"tag": "<tag>", "max_distance_m": 0.5, "for_ticks": 3}}Robot stays within max_distance_m of a tagged object for for_ticks.
{"elapsed_ticks": <int>}A tick count is reached.
{"flipped": true}Robot has flipped/fallen.

​
Reward terms

All optional and additive per tick:
TermEffect
step_costConstant per-tick reward. Set negative as a time penalty.
distance_to_zone{zone, weight} → weight × (prev_dist − now_dist) to the zone center. Positive = getting closer.
distance_to_tag{tag, weight} → same, but to the first object with that tag.
forward_distance_gainscalar × (prev_x − now_x). Rewards moving forward (−X).
contact_with_rubble_penaltyPer-tick penalty for being within 0.25 m of any rubble-tagged object.
fall_penaltyApplied each tick roll/pitch exceeds 60°.
phase_success_bonusOne-shot bonus when success_when fires.
phase_failure_penaltyOne-shot penalty when fail_when fires.

​
vla_finetune

"vla_finetune": {
  "prompt_template": "[MISSION: {mission_name}] [PHASE {phase_idx}/{n_phases}: {phase_name}]\n[GOAL: {goal_prompt}]\n[OBS] ...\n[ACTION]",
  "include_failures": true
}
FieldMeaning
prompt_templateFormat string for each exported row. Placeholders: {mission_name}, {phase_idx}, {n_phases}, {phase_name}, {goal_prompt}.
include_failuresIf true, failed-phase transitions are also exported.
This template renders the prompt field in <run-id>.finetune.jsonl and in env finetune output. Feed those rows straight into a VLA SFT or offline-RL pipeline.