Embedded-Based Object Matching and Robot Arm Control

Le, Minh-Tri; Li, Chih-Hung G.; Guo, Shu‐Mei; Lien, Jenn-Jier James

doi:10.1109/coase.2019.8843182

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, MP is not designed to plan through complex manipulation tasks requiring environmental interaction. Furthermore, MP necessitates the specification of a goal state in the robot's frame of reference, which is typically accomplished through manual engineering [4], template matching [5], or an object-specific pose estimator [6] trained on manually labeled data. 1 Applied AI Lab (A2I), Oxford Robotics Institute, University of Oxford Correspondence to: jyamada@robots.ox.ac.uk Fig.…”

Section: Introductionmentioning

confidence: 99%

Efficient Skill Acquisition for Complex Manipulation Tasks in Obstructed Environments

Yamada¹,

Collins²,

Posner³

2023

Preprint

View full text Add to dashboard Cite

Data efficiency in robotic skill acquisition is crucial for operating robots in varied small-batch assembly settings. To operate in such environments, robots must have robust obstacle avoidance and versatile goal conditioning acquired from only a few simple demonstrations. Existing approaches, however, fall short of these requirements. Deep reinforcement learning (RL) enables a robot to learn complex manipulation tasks but is often limited to small task spaces in the real world due to sample inefficiency and safety concerns. Motion planning (MP) can generate collision-free paths in obstructed environments, but cannot solve complex manipulation tasks and requires goal states often specified by a user or objectspecific pose estimator. In this work, we propose a system for efficient skill acquisition that leverages an object-centric generative model (OCGM) for versatile goal identification to specify a goal for MP combined with RL to solve complex manipulation tasks in obstructed environments. Specifically, OCGM enables one-shot target object identification and reidentification in new scenes, allowing MP to guide the robot to the target object while avoiding obstacles. This is combined with a skill transition network, which bridges the gap between terminal states of MP and feasible start states of a sampleefficient RL policy. The experiments demonstrate that our OCGM-based one-shot goal identification provides competitive accuracy to other baseline approaches and that our modular framework outperforms competitive baselines, including a stateof-the-art RL algorithm, by a significant margin for complex manipulation tasks in obstructed environments.

show abstract