QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation

arXiv cs.AI / 4/27/2026

💬 OpinionDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The paper introduces QDTraj, a method for generating diverse low-level robot trajectory primitives to manipulate a wide range of articulated household objects.
It emphasizes that generating expert trajectories must account for multiple solution diversity, enabling robots to select robust behaviors under real-world constraints and unexpected changes.
QDTraj uses Quality-Diversity algorithms with sparse reward exploration to produce a set of trajectory primitives that are both diverse and high-performing for a given manipulation task.
Experiments show QDTraj produces at least 5× more diverse trajectories than compared methods for hinge and slider activation tasks in both simulation and real-world deployment.
The approach generalizes across 30 articulations from the PartNetMobility dataset, averaging 704 different trajectories per task, and the authors provide public code online.

Abstract

Thanks to the latest advances in learning and robotics, domestic robots are beginning to enter homes, aiming to execute household chores autonomously. However, robots still struggle to perform autonomous manipulation tasks in open-ended environments. In this context, this paper presents a method that enables a robot to manipulate a wide spectrum of articulated objects. In this paper, we automatically generate different robot low-level trajectory primitives to manipulate given object articulations. A very important point when it comes to generating expert trajectories is to consider the diversity of solutions to achieve the same goal. Indeed, knowing diverse low-level primitives to accomplish the same task enables the robot to choose the optimal solution in its real-world environment, with live constraints and unexpected changes. To do so, we propose a method based on Quality-Diversity algorithms that leverages sparse reward exploration in order to generate a set of diverse and high-performing trajectory primitives for a given manipulation task. We validated our method, QDTraj, by generating diverse trajectories in simulation and deploying them in the real world. QDTraj generates at least 5 times more diverse trajectories for both hinge and slider activation tasks, outperforming the other methods we compared against. We assessed the generalization of our method over 30 articulations of the PartNetMobility articulated object dataset, with an average of 704 different trajectories by task. Code is publicly available at: https://kappel.web.isir.upmc.fr/trajectory_primitive_website