Timezone: »
Training long-horizon robotic policies in complex physical environments is essential for many applications, such as robotic manipulation. However, learning a policy that can generalize to unseen tasks is challenging. In this work, we propose to achieve one-shot task generalization by decoupling plan generation and plan execution. Specifically, our method solves complex long-horizon tasks in three steps: build a paired abstract environment by simplifying geometry and physics, generate abstract trajectories, and solve the original task by an abstract-to-executable trajectory translator. In the abstract environment, complex dynamics such as physical manipulation are removed, making abstract trajectories easier to generate. However, this introduces a large domain gap between abstract trajectories and the actual executed trajectories as abstract trajectories lack low-level details and aren’t aligned frame-to-frame with the executed trajectory. In a manner reminiscent of language translation, our approach leverages a seq-to-seq model to overcome the large domain gap between the abstract and executable trajectories, enabling the low-level policy to follow the abstract trajectory. Experimental results on various unseen long-horizon tasks with different robot embodiments demonstrate the practicability of our methods to achieve one-shot task generalization. Videos and more details can be found in the supplementary materials and project page: https://sites.google.com/view/abstract-to-executable/
Author Information
Stone Tao (University of California - San Diego)
Xiaochen Li (University of California, San Diego)
Tongzhou Mu (University of California, San Diego)
Zhiao Huang (University of California San Diego)
Yuzhe Qin (University of California, San Diego, University of California, San Diego)
Hao Su (UCSD)
More from the Same Authors
-
2021 : ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations »
Tongzhou Mu · Zhan Ling · Fanbo Xiang · Derek Yang · Xuanlin Li · Stone Tao · Zhiao Huang · Zhiwei Jia · Hao Su -
2021 : From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation »
Yuzhe Qin · Hao Su · Xiaolong Wang -
2021 : Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization »
Minghao Zhang · Ruihan Yang · Yuzhe Qin · Xiaolong Wang -
2021 : Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization »
Chieko Imai · Minghao Zhang · Ruihan Yang · Yuzhe Qin · Xiaolong Wang -
2022 : On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning »
yifan xu · Nicklas Hansen · Zirui Wang · Yung-Chieh Chan · Hao Su · Zhuowen Tu -
2022 : Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation »
Yuzhe Qin · Binghao Huang · Zhao-Heng Yin · Hao Su · Xiaolong Wang -
2022 : VARIATIONAL REPARAMETRIZED POLICY LEARNING WITH DIFFERENTIABLE PHYSICS »
Zhiao Huang · Litian Liang · Zhan Ling · Xuanlin Li · Chuang Gan · Hao Su -
2022 : Multi-skill Mobile Manipulation for Object Rearrangement »
Jiayuan Gu · Devendra Singh Chaplot · Hao Su · Jitendra Malik -
2022 : MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations »
Nicklas Hansen · Yixin Lin · Hao Su · Xiaolong Wang · Vikash Kumar · Aravind Rajeswaran -
2022 : On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning »
yifan xu · Nicklas Hansen · Zirui Wang · Yung-Chieh Chan · Hao Su · Zhuowen Tu -
2022 : Emergent collective intelligence from massive-agent cooperation and competition »
Hanmo Chen · Stone Tao · JIAXIN CHEN · Weihan Shen · Xihui Li · Chenghui Yu · Sikai Cheng · Xiaolong Zhu · Xiu Li -
2023 Competition: Lux AI Challenge Season 2 NeurIPS Edition »
· Qimai Li · Yuhao Jiang · JIAXIN CHEN · Xiaolong Zhu · Bovard Doerschuk-Tiberi · Isabelle Pan · Addison Howard -
2021 Poster: Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation »
Nicklas Hansen · Hao Su · Xiaolong Wang -
2021 Poster: Particle Cloud Generation with Message Passing Generative Adversarial Networks »
Raghav Kansal · Javier Duarte · Hao Su · Breno Orzari · Thiago Tomei · Maurizio Pierini · Mary Touranakou · jean-roch vlimant · Dimitrios Gunopulos -
2020 Poster: Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs »
Hao Tang · Zhiao Huang · Jiayuan Gu · Bao-Liang Lu · Hao Su -
2020 Poster: Multi-task Batch Reinforcement Learning with Metric Learning »
Jiachen Li · Quan Vuong · Shuang Liu · Minghua Liu · Kamil Ciosek · Henrik Christensen · Hao Su -
2020 Poster: Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals »
Tongzhou Mu · Jiayuan Gu · Zhiwei Jia · Hao Tang · Hao Su -
2019 Poster: Mapping State Space using Landmarks for Universal Goal Reaching »
Zhiao Huang · Fangchen Liu · Hao Su -
2018 Poster: Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions »
Minhyuk Sung · Hao Su · Ronald Yu · Leonidas Guibas -
2017 Poster: PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space »
Charles Ruizhongtai Qi · Li Yi · Hao Su · Leonidas Guibas -
2016 Poster: FPNN: Field Probing Neural Networks for 3D Data »
Yangyan Li · Soeren Pirk · Hao Su · Charles R Qi · Leonidas Guibas -
2010 Poster: Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification »
Li-Jia Li · Hao Su · Eric Xing · Li Fei-Fei