AI Habitat · JSON Structure

Ai Habitat Agent Config Structure

Configuration for an agent in the simulation

Type: object Properties: 5
Artificial IntelligenceSimulationEmbodied AIRoboticsComputer VisionReinforcement LearningMachine LearningOpen SourceResearch

AgentConfig is a JSON Structure definition published by AI Habitat, describing 5 properties. It conforms to the https://json-structure.org/meta/core/v0/# meta-schema.

Properties

height radius sensor_specifications action_space body_type

Meta-schema: https://json-structure.org/meta/core/v0/#

JSON Structure

ai-habitat-agent-config-structure.json Raw ↑ 
{
  "$schema": "https://json-structure.org/meta/core/v0/#",
  "$id": "https://raw.githubusercontent.com/api-evangelist/ai-habitat/refs/heads/main/json-structure/ai-habitat-agent-config-structure.json",
  "name": "AgentConfig",
  "description": "Configuration for an agent in the simulation",
  "type": "object",
  "properties": {
    "height": {
      "type": "double",
      "description": "Agent height in meters",
      "example": 1.5
    },
    "radius": {
      "type": "double",
      "description": "Agent radius in meters for collision",
      "example": 0.1
    },
    "sensor_specifications": {
      "type": "array",
      "description": "List of sensor specs attached to agent",
      "items": {
        "type": "object"
      }
    },
    "action_space": {
      "type": "object",
      "description": "Discrete action space mapping action names to ActionSpec"
    },
    "body_type": {
      "type": "string",
      "description": "Agent body type: LocoBot, FetchRobot, Franka, AlienGo",
      "example": "LocoBot"
    }
  }
}