# Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following

arXiv: https://arxiv.org/abs/2304.03767 · HTML: https://mlsanity.com/paper/2304.03767/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 92 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Builds on (most cited first, 30 of 66)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks](https://mlsanity.com/paper/2108.03272/) (2021)
- [Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks](https://mlsanity.com/paper/1911.07883/) (2019)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)

## Built on by (most cited first, 9 of 9)

- [A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models](https://mlsanity.com/paper/2308.07997/) (2023)
- [Learning Vision-and-Language Navigation from YouTube Videos](https://mlsanity.com/paper/2307.11984/) (2023)
- [ThinkBot: Embodied Instruction Following with Thought Chain Reasoning](https://mlsanity.com/paper/2312.07062/) (2023)
- [GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs](https://mlsanity.com/paper/2311.04901/) (2023)
- [Advancing Visual Grounding with Scene Knowledge: Benchmark and Method](https://mlsanity.com/paper/2307.11558/) (2023)
- [Generalizable Long-Horizon Manipulations with Large Language Models](https://mlsanity.com/paper/2310.02264/) (2023)
- [Embodied Instruction Following in Unknown Environments](https://mlsanity.com/paper/2406.11818/) (2024)
- [Learning to Play Video Games with Intuitive Physics Priors](https://mlsanity.com/paper/2409.13886/) (2024)
- [On Extending Semantic Abstraction for Efficient Search of Hidden Objects](https://mlsanity.com/paper/2512.22220/) (2025)

## Abstract (arXiv)

Humans, even at a very early age, can learn visual concepts and understand geometry and layout through active interaction with the environment, and generalize their compositions to complete tasks described by natural languages in novel scenes. To mimic such capability, we propose Embodied Concept Learner (ECL) in an interactive 3D environment. Specifically, a robot agent can ground visual concepts, build semantic maps and plan actions to complete tasks by learning purely from human demonstrations and language instructions, without access to ground-truth semantic and depth supervisions from simulations. ECL consists of: (i) an instruction parser that translates the natural languages into executable programs; (ii) an embodied concept learner that grounds visual concepts based on language descriptions; (iii) a map constructor that estimates depth and constructs semantic maps by leveraging the learned concepts; and (iv) a program executor with deterministic policies to execute each program. ECL has several appealing benefits thanks to its modularized design. Firstly, it enables the robotic agent to learn semantics and depth unsupervisedly acting like babies, e.g., ground concepts through active interaction and perceive depth by disparities when moving forward. Secondly, ECL is fully transparent and step-by-step interpretable in long-term planning. Thirdly, ECL could be beneficial for the embodied instruction following (EIF), outperforming previous works on the ALFRED benchmark when the semantic label is not provided. Also, the learned concept can be reused for other downstream tasks, such as reasoning of object states. Project page: http://ecl.csail.mit.edu/