# Transformers for One-Shot Visual Imitation

arXiv: https://arxiv.org/abs/2011.05970 · HTML: https://mlsanity.com/paper/2011.05970/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 30 of 78)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [RVT: Robotic View Transformer for 3D Object Manipulation](https://mlsanity.com/paper/2306.14896/) (2023)
- [What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2204.06252/) (2022)
- [RVT-2: Learning Precise Manipulation from Few Demonstrations](https://mlsanity.com/paper/2406.08545/) (2024)
- [Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions](https://mlsanity.com/paper/2309.10150/) (2023)
- [RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation](https://mlsanity.com/paper/2306.11706/) (2023)
- [Generalized Decision Transformer for Offline Hindsight Information Matching](https://mlsanity.com/paper/2111.10364/) (2021)
- [From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data](https://mlsanity.com/paper/2210.10047/) (2022)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Vision Language Models are In-Context Value Learners](https://mlsanity.com/paper/2411.04549/) (2024)
- [Preference Transformer: Modeling Human Preferences using Transformers for RL](https://mlsanity.com/paper/2303.00957/) (2023)
- [XSkill: Cross Embodiment Skill Discovery](https://mlsanity.com/paper/2307.09955/) (2023)
- [Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation](https://mlsanity.com/paper/2410.08001/) (2024)
- [The Ingredients for Robotic Diffusion Transformers](https://mlsanity.com/paper/2410.10088/) (2024)
- [Imitating Task and Motion Planning with Visuomotor Transformers](https://mlsanity.com/paper/2305.16309/) (2023)
- [Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers](https://mlsanity.com/paper/2403.12943/) (2024)
- [A Survey on Transformers in Reinforcement Learning](https://mlsanity.com/paper/2301.03044/) (2023)
- [Towards More Generalizable One-shot Visual Imitation Learning](https://mlsanity.com/paper/2110.13423/) (2021)
- [HRP: Human Affordances for Robotic Pre-Training](https://mlsanity.com/paper/2407.18911/) (2024)
- [RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulation](https://mlsanity.com/paper/2411.02704/) (2024)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations](https://mlsanity.com/paper/2507.00990/) (2025)

## Abstract (arXiv)

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate that into concrete motor control. Is it possible to give a robot this same capability? Prior research in robot imitation learning has created agents which can acquire diverse skills from expert human operators. However, expanding these techniques to work with a single positive example during test time is still an open challenge. Apart from control, the difficulty stems from mismatches between the demonstrator and robot domains. For example, objects may be placed in different locations (e.g. kitchen layouts are different in every house). Additionally, the demonstration may come from an agent with different morphology and physical appearance (e.g. human), so one-to-one action correspondences are not available. This paper investigates techniques which allow robots to partially bridge these domain gaps, using their past experience. A neural network is trained to mimic ground truth robot actions given context video from another agent, and must generalize to unseen task instances when prompted with new videos during test time. We hypothesize that our policy representations must be both context driven and dynamics aware in order to perform these tasks. These assumptions are baked into the neural network using the Transformers attention mechanism and a self-supervised inverse dynamics loss. Finally, we experimentally determine that our method accomplishes a ~ 2x improvement in terms of task success rate over prior baselines in a suite of one-shot manipulation tasks.