paper-with-me

홈 › Papers

Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy

2024-06-23 · Chen Wang, Kaiyi Ji, Junyi Geng, Zhongqiang Ren, Taimeng Fu, Fan Yang, Yifan Guo, Haonan He, Xiangyu Chen, Zitong Zhan, Qiwei Du, Shaoshu Su, Bowen Li, Yuheng Qiu, Yi Du, Qihang Li, Yifan Yang, Xiao Lin, Zhipeng Zhao

Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from generalizing well to ever-changing environments. Moreover, labeling data for robotic tasks is often impractical and expensive. To overcome these challenges, we introduce a new self-supervised neuro-symbolic (NeSy) computational framework, imperative learning (IL), for robot autonomy, leveraging the generalization abilities of symbolic reasoning. The framework of IL consists of three primary components: a neural module, a reasoning engine, and a memory system. We formulate IL as a special bilevel optimization (BLO), which enables reciprocal learning over the three modules. This overcomes the label-intensive obstacles associated with data-driven approaches and takes advantage of symbolic reasoning concerning logical reasoning, physical principles, geometric analysis, etc. We discuss several optimization techniques for IL and verify their effectiveness in five distinct robot autonomy tasks including path planning, rule induction, optimal control, visual odometry, and multi-robot routing. Through various experiments, we show that IL can significantly enhance robot autonomy capabilities and we anticipate that it will catalyze further research across diverse domains.

📄 PDF Abstract BibTeX arXiv:2406.16087

Code (0)

등록된 구현이 없습니다.

Tasks

Bilevel OptimizationImitation LearningLogical ReasoningVisual Odometry

Similar Papers 제목 키워드 기반

Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs

2022-01-23 · NeurIPS 2021 12 · Taebum Kim, Eunji Jeong, Geon-Woo Kim, Yunmo Koo 외

Imperative programming allows users to implement their deep neural networks (DNNs) easily and has become an essential part of recent deep learning (DL) frameworks. Recently, several systems have been proposed to combine …

Deep Learning

Learning Symbolic Representations Through Joint GEnerative and DIscriminative Training

2023-04-22 · Emanuele Sansone, Robin Manhaeve

We introduce GEDI, a Bayesian framework that combines existing self-supervised learning objectives with likelihood-based generative models. This framework leverages the benefits of both GEnerative and DIscriminative appr…

ClusteringSelf-Supervised Learning

Symbolic Techniques for Deep Learning: Challenges and Opportunities

2020-10-01 · Belinda Fang, Elaine Yang, Fei Xie

As the number of deep learning frameworks increase and certain ones gain popularity, it spurs the discussion of what methodologies are employed by these frameworks and the reasoning behind them. The goal of this survey i…

Deep Learning

NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-Language

2025-09-30 · Danial Kamali, Parisa Kordjamshidi arxiv

Modern Vision-Language Models (VLMs) have achieved impressive performance in various tasks, yet they often struggle with compositional reasoning, the ability to decompose and recombine concepts to solve novel problems. W…

Natural Language QueriesVisual Reasoning

NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval

2024-04-17 · Sanggeon Yun, Ryozo Masukawa, Sungheon Jeong, Mohsen Imani

Customizable image retrieval from large datasets remains a critical challenge, particularly when preserving spatial relationships within images. Traditional hashing methods, primarily based on deep learning, often fail t…

Image RetrievalRetrieval