RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches

TL;DR

RT-Trajectory introduces a novel approach for robotic task generalization using rough trajectory sketches, enabling robots to adapt to new tasks more effectively by interpreting simple human or automated inputs.

Contribution

The paper presents RT-Trajectory, a practical policy conditioning method that leverages trajectory sketches for improved generalization to new robotic tasks.

Findings

RT-Trajectory outperforms language-conditioned policies in task versatility.

Trajectory sketches enable effective task communication and generalization.

The approach is validated on diverse real-world robotic tasks.

Abstract

Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts, generalization to new tasks remains challenging. For example, a language-conditioned policy trained on pick-and-place tasks will not be able to generalize to a folding task, even if the arm trajectory of folding is similar to pick-and-place. Our key insight is that this kind of generalization becomes feasible if we represent the task through rough trajectory sketches. We propose a policy conditioning method using such rough trajectory sketches, which we call RT-Trajectory, that is practical, easy to specify, and allows the policy to effectively perform new tasks that would otherwise be challenging to perform. We find that trajectory sketches strike a balance between being detailed enough to express low-level motion-centric guidance while being coarse enough to allow the learned policy to interpret the trajectory sketch in the context of situational visual observations. In addition, we show how trajectory sketches can provide a useful interface to communicate with robotic policies: they can be specified through simple human inputs like drawings or videos, or through automated methods such as modern image-generating or waypoint-generating methods. We evaluate RT-Trajectory at scale on a variety of real-world robotic tasks, and find that RT-Trajectory is able to perform a wider range of tasks compared to language-conditioned and goal-conditioned policies, when provided the same training data.