中文
相关论文

相关论文: Neuro-Symbolic Imitation Learning: Discovering Sym…

200 篇论文

Humans can infer concepts from image pairs and apply those in the physical world in a completely different setting, enabling tasks like IKEA assembly from diagrams. If robots could represent and infer high-level concepts, it would…

人工智能 · 计算机科学 2018-12-10 Miguel Lázaro-Gredilla , Dianhuan Lin , J. Swaroop Guntupalli , Dileep George

In this paper, we discuss a framework for teaching bimanual manipulation tasks by imitation. To this end, we present a system and algorithms for learning compliant and contact-rich robot behavior from human demonstrations. The presented…

机器人学 · 计算机科学 2022-08-02 Simon Stepputtis , Maryam Bandari , Stefan Schaal , Heni Ben Amor

We tackle real-world long-horizon robot manipulation tasks through skill discovery. We present a bottom-up approach to learning a library of reusable skills from unsegmented demonstrations and use these skills to synthesize prolonged robot…

机器人学 · 计算机科学 2022-01-25 Yifeng Zhu , Peter Stone , Yuke Zhu

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…

In this paper, we study the problem of enabling a vision-based robotic manipulation system to generalize to novel tasks, a long-standing challenge in robot learning. We approach the challenge from an imitation learning perspective, aiming…

机器人学 · 计算机科学 2022-02-07 Eric Jang , Alex Irpan , Mohi Khansari , Daniel Kappler , Frederik Ebert , Corey Lynch , Sergey Levine , Chelsea Finn

Learning fine-grained movements is a challenging topic in robotics, particularly in the context of robotic hands. One specific instance of this challenge is the acquisition of fingerspelling sign language in robots. In this paper, we…

机器人学 · 计算机科学 2024-07-25 Federico Tavella , Aphrodite Galata , Angelo Cangelosi

As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…

人工智能 · 计算机科学 2017-06-02 Yordan Hristov , Svetlin Penkov , Alex Lascarides , Subramanian Ramamoorthy

This paper explores the potential of abstracting complex visual information into discrete, structured symbolic sequences using self-supervised learning (SSL). Inspired by how language abstracts and organizes information to enable better…

计算机视觉与模式识别 · 计算机科学 2025-03-10 Victor Sebastian Martinez Pozos , Ivan Vladimir Meza Ruiz

We introduce the concept of a \textbf{neuro-symbolic pair} -- neural and symbolic approaches that are linked through a common knowledge representation. Next, we present \textbf{taxonomic networks}, a type of discrimination network in which…

人工智能 · 计算机科学 2025-06-02 Zekun Wang , Ethan L. Haarer , Nicki Barari , Christopher J. MacLellan

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…

机器学习 · 计算机科学 2020-11-12 Sudeep Dasari , Abhinav Gupta

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Matthew Gwilliam , Xiao Wang , Xuefeng Hu , Zhenheng Yang

Neurosymbolic AI is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs are becoming a popular way to represent heterogeneous and…

人工智能 · 计算机科学 2025-01-13 Lauren Nicole DeLong , Ramon Fernández Mir , Jacques D. Fleuriot

Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have shown their…

动力系统 · 数学 2026-05-07 Nibodh Boddupalli , Timothy Matchen , Jeff Moehlis

The paper tackles four basic questions associated with human brain as a learning system. How can the brain learn to (1) mentally simulate different external memory aids, (2) perform, in principle, any mental computations using imaginary…

人工智能 · 计算机科学 2009-01-12 Victor Eliashberg

In this paper we present a neurosymbolic architecture for coupling language-guided visual reasoning with robot manipulation. A non-expert human user can prompt the robot using unconstrained natural language, providing a referring expression…

机器人学 · 计算机科学 2025-12-16 Georgios Tziafas , Hamidreza Kasaei

Amidst the wide popularity of imitation learning algorithms in robotics, their properties regarding hyperparameter sensitivity, ease of training, data efficiency, and performance have not been well-studied in high-precision…

机器人学 · 计算机科学 2024-08-27 Michael Drolet , Simon Stepputtis , Siva Kailas , Ajinkya Jain , Jan Peters , Stefan Schaal , Heni Ben Amor

Inspired by the brain, deep neural networks (DNN) are thought to learn abstract representations through their hierarchical architecture. However, at present, how this happens is not well understood. Here, we demonstrate that DNN learn…

机器学习 · 计算机科学 2015-02-16 Andrew J. R. Simpson

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…

人工智能 · 计算机科学 2021-02-22 Nicolas Duminy , Sao Mai Nguyen , Junshuai Zhu , Dominique Duhaut , Jerome Kerdreux

This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible computational and biological representations by correlating…

计算机视觉与模式识别 · 计算机科学 2020-04-21 Simone Palazzo , Concetto Spampinato , Isaak Kavasidis , Daniela Giordano , Joseph Schmidt , Mubarak Shah

People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in…

人工智能 · 计算机科学 2017-03-09 Abhishek Gupta , Coline Devin , YuXuan Liu , Pieter Abbeel , Sergey Levine