What's the Move? Hybrid Imitation Learning via Salient Points

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sundaresan, Priya, Hu, Hengyuan, Vuong, Quan, Bohg, Jeannette, Sadigh, Dorsa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912147718537216
author Sundaresan, Priya
Hu, Hengyuan
Vuong, Quan
Bohg, Jeannette
Sadigh, Dorsa
author_facet Sundaresan, Priya
Hu, Hengyuan
Vuong, Quan
Bohg, Jeannette
Sadigh, Dorsa
contents While imitation learning (IL) offers a promising framework for teaching robots various behaviors, learning complex tasks remains challenging. Existing IL policies struggle to generalize effectively across visual and spatial variations even for simple tasks. In this work, we introduce SPHINX: Salient Point-based Hybrid ImitatioN and eXecution, a flexible IL policy that leverages multimodal observations (point clouds and wrist images), along with a hybrid action space of low-frequency, sparse waypoints and high-frequency, dense end effector movements. Given 3D point cloud observations, SPHINX learns to infer task-relevant points within a point cloud, or salient points, which support spatial generalization by focusing on semantically meaningful features. These salient points serve as anchor points to predict waypoints for long-range movement, such as reaching target poses in free-space. Once near a salient point, SPHINX learns to switch to predicting dense end-effector movements given close-up wrist images for precise phases of a task. By exploiting the strengths of different input modalities and action representations for different manipulation phases, SPHINX tackles complex tasks in a sample-efficient, generalizable manner. Our method achieves 86.7% success across 4 real-world and 2 simulated tasks, outperforming the next best state-of-the-art IL baseline by 41.1% on average across 440 real world trials. SPHINX additionally generalizes to novel viewpoints, visual distractors, spatial arrangements, and execution speeds with a 1.7x speedup over the most competitive baseline. Our website (http://sphinx-manip.github.io) provides open-sourced code for data collection, training, and evaluation, along with supplementary videos.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05426
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle What's the Move? Hybrid Imitation Learning via Salient Points
Sundaresan, Priya
Hu, Hengyuan
Vuong, Quan
Bohg, Jeannette
Sadigh, Dorsa
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
While imitation learning (IL) offers a promising framework for teaching robots various behaviors, learning complex tasks remains challenging. Existing IL policies struggle to generalize effectively across visual and spatial variations even for simple tasks. In this work, we introduce SPHINX: Salient Point-based Hybrid ImitatioN and eXecution, a flexible IL policy that leverages multimodal observations (point clouds and wrist images), along with a hybrid action space of low-frequency, sparse waypoints and high-frequency, dense end effector movements. Given 3D point cloud observations, SPHINX learns to infer task-relevant points within a point cloud, or salient points, which support spatial generalization by focusing on semantically meaningful features. These salient points serve as anchor points to predict waypoints for long-range movement, such as reaching target poses in free-space. Once near a salient point, SPHINX learns to switch to predicting dense end-effector movements given close-up wrist images for precise phases of a task. By exploiting the strengths of different input modalities and action representations for different manipulation phases, SPHINX tackles complex tasks in a sample-efficient, generalizable manner. Our method achieves 86.7% success across 4 real-world and 2 simulated tasks, outperforming the next best state-of-the-art IL baseline by 41.1% on average across 440 real world trials. SPHINX additionally generalizes to novel viewpoints, visual distractors, spatial arrangements, and execution speeds with a 1.7x speedup over the most competitive baseline. Our website (http://sphinx-manip.github.io) provides open-sourced code for data collection, training, and evaluation, along with supplementary videos.
title What's the Move? Hybrid Imitation Learning via Salient Points
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.05426