Instruction-driven history-aware policies for robotic manipulations

Pierre-Louis Guhur, Shizhe Chen, Ricardo Garcia Pinel, Makarand Tapaswi, Ivan Laptev, Cordelia Schmid

Keywords: Robotics Manipulation, Language Instruction, Transformer

TL;DR: A new model to solve robotics tasks using instructions, multi-views and history

Abstract: In human environments, robots are expected to accomplish a variety of manipulation tasks given simple natural language instructions. Yet, robotic manipulation is extremely challenging as it requires fine-grained motor control, long-term memory as well as generalization to previously unseen tasks and environments. To address these challenges, we propose a unified transformer-based approach that takes into account multiple inputs. In particular, our transformer architecture integrates (i) natural language instructions and (ii) multi-view scene observations while (iii) keeping track of the full history of observations and actions. Such an approach enables learning dependencies between history and instructions and improves manipulation precision using multiple views. We evaluate our method on the challenging RLBench benchmark and on a real-world robot. Notably, our approach scales to 74 diverse RLBench tasks and outperforms the state of the art. We also address instruction-conditioned tasks and demonstrate excellent generalization to previously unseen variations.

Student First Author: yes

Website: https://guhur.github.io/hiveformer

Code: https://github.com/guhur/hiveformer

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2209.04899/code)