We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, and benchmark tasks. Specifically, we present: (i) ReplicaCAD: an artist-authored, annotated, reconfigurable 3D dataset of apartments (matching real spaces) with articulated objects (e.g. cabinets and drawers that can open/close); (ii) H2.0: a high-performance physics-enabled 3D simulator with speeds exceeding 25,000 simulation steps per second (850x real-time) on an 8-GPU node, representing 100x speed-ups over prior work; and, (iii) Home Assistant Benchmark (HAB): a suite of common tasks for assistive robots (tidy the house, prepare groceries, set the table) that test a range of mobile manipulation capabilities. These large-scale engineering contributions allow us to systematically compare deep reinforcement learning (RL) at scale and classical sense-plan-act (SPA) pipelines in long-horizon structured tasks, with an emphasis on generalization to new objects, receptacles, and layouts. We find that (1) flat RL policies struggle on HAB compared to hierarchical ones; (2) a hierarchy with independent skills suffers from 'hand-off problems', and (3) SPA pipelines are more brittle than RL policies.

介绍 Habitat 2.0(H2.0) 为一种用于在交互式 3D 环境和复杂的物理启用技术中训练虚拟机器人的仿真平台。在数据、仿真和基准任务的所有层面上都做出了全面的贡献。使用 HAB 测试移动操作能力。比较 deep RL 和 SPA 管道。发现 flat RL 与独立技能的层次结构存在 “hand-off” 问题，同时 SPA 传统管道比 RL 策略更脆弱。

Habitat 2.0: 训练家居助手重新排列他们的生活空间