CHALET: Cornell House Agent Learning Environment

By Claudia Yan, Dipendra Kumar Misra, Andrew Bennett, Aaron Walsman, Yonatan Bisk, Yoav Artzi. 2018

101 citations recorded by the source corpus.

We present CHALET, a 3D house simulator with support for navigation and manipulation. CHALET includes 58 rooms and 10 house configuration, and allows to easily create new house and room layouts. CHALET supports a range of common household activities, including moving objects, toggling appliances, and placing objects inside closeable containers. The environment and actions available are designed to create a challenging domain to train and evaluate autonomous agents, including for tasks that combine language, vision, and planning in a dynamic environment.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Social Psychology, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Social Psychology

In Reinforcement Learning

Citations in the corpus

Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, background): “How are interactive simulators built today? Either by relying on game engines [7, 51, 52] or via a ‘homebrew’ integration of existing rendering and physics libraries [8, 35, 37, 53].”
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments (2017, methodology): “The main advantage of our framework over synthetic environments [30, 10, 58, 59] is that all pixel observations come from natural images of real scenes, ensuring that almost every coffee mug, pot-plant and wallpaper texture is unique.”
A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “CHALET Cornell House Agent Learning Environment [20] is an interactive home-based environment which allows for navigation and manipulation of both the objects and the environment.”
Habitat: A Platform for Embodied AI Research (2019, background): “The availability of large-scale 3D scene datasets [4, 25, 7] and community interest in active vision tasks led to a recent surge of work that resulted in the development of a variety of simulation platforms for indoor environments [16, 6, 12, 22, 27, 2, 28, 29, 21].”
A Survey of Reinforcement Learning Informed by Natural Language (2019, background): “One starting point is provided by extending 3D house simulation environments [Gordon et al. , 2018; Das et al. , 2018a; Yan et al. , 2018] some of which already support generation and evaluation of templated instructions.”
TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments (2018, background): “The larger environment requires following the instructions closely, as ﬁnding the goal using search strategies is unlikely, even given a large number of steps.”
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (2019, background): “…Navigation (VLN) tasks, agents must follow natural language navigation instructions through either simulated (Macmahon et al., 2006; Yan et al., 2018; Bisk et al., 2018; Shah et al., 2018), simulations of realistic (Blukis et al., 2018; Misra et al., 2018) and real environments…”
Environments for Lifelong Reinforcement Learning (2018, background): “These beneﬁts also set it apart from other environments like AI2-THOR [Zhu et al., 2017] which supports only 32 single-room environments or CHALET [Yan et al., 2018] in which only a small set of discrete actions are supported.”
What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning (2019, background): “More recently, multiple environments have been created which offer near-photorealistic and physically accurate interaction such as AI2THOR [20], Gibson [34], and CHALET [35].”
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding (2018, unknown): “data through physical simulation engines [20, 43, 29].”
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents (2021, background): “Beyond video game environments, many home environment simulators have been proposed recently (Brodeur et al., 2017; Savva et al., 2017; Puig et al., 2018; Yan et al., 2018; Gao et al., 2019; Savva et al., 2019) which offer visuallyrealistic scenes for evaluating Embodied AI.”
SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation (2019, background): “These concerns, as well as the difficulty in parallelizing and reproducing experiments at a low cost, have drawn research interest towards simulation environments [3, 15, 35, 36, 20].”
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation (2019, background): “CHALET [42] is another interactable synthetic indoor environment with larger interactive action space.”
Unity: A General Platform for Intelligent Agents (2018, methodology): “In the same vein, the Chalet platform uses Unity to provide a set of indoor navigation environments (Yan et al., 2018).”
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, background): “Some of the platforms are built towards this effort [12, 46, 100, 105, 109].”
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform (2020, background): “In recent years, several synthetic frameworks have been proposed to investigate tasks including visual navigation, task completion and question answering in indoor scenes [32, 53, 70, 8, 74, 72, 46, 54].”
Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction (2018, methodology): “Yan et al. (2018) provides the full details of the simulator and evaluation.”
CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration (2022, background): “…exploration, many navigation tasks are “goal-conditioned,” where the agent needs to navigate to a given position (i.e., point goal [58, 72, 74, 67, 11, 30]), a view of the environment (i.e., image goal [78, 43, 56]), or a specified object category (i.e., object goal [69, 10, 9, 75, 39, 1,…”