Neuromorphic Robot Dream

2016-07-27 · Alexander Tchitchigin, Max Talanov, Larisa Safina, Manuel Mazzara

In this paper we present the next step in our approach to neurobiologically plausible implementation of emotional reactions and behaviors for real-time autonomous robotic systems. The working metaphor we use is the "day" and the "night" phases of mammalian life. During the "day phase" a robotic system stores the inbound information and is controlled by a light-weight rule-based system in real time. In contrast to that, during the "night phase" information that has been stored is transferred to a supercomputing system to update the realistic neural network: emotional and behavioral strategies.

📄 PDF Abstract BibTeX arXiv:1607.08131

Code (0)

등록된 구현이 없습니다.

Neuromorphic dreaming: A pathway to efficient learning in artificial agents

2024-05-24 · Ingo Blakowski, Dmitrii Zendrikov, Cristiano Capone, Giacomo Indiveri

Achieving energy efficiency in learning is a key challenge for artificial intelligence (AI) computing platforms. Biological systems demonstrate remarkable abilities to learn complex skills quickly and efficiently. Inspir…

Model-based Reinforcement Learning

DayDreamer: World Models for Physical Robot Learning

2022-06-28 · Philipp Wu, Alejandro Escontrela, Danijar Hafner, Ken Goldberg 외

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deplo…

Deep Reinforcement Learning Navigate reinforcement-learning Reinforcement Learning (RL)

DreamGen: Unlocking Generalization in Robot Learning through Video World Models

2025-05-19 · Joel Jang, Seonghyeon Ye, Zongyu Lin, Jiannan Xiang 외

We introduce DreamGen, a simple yet highly effective 4-stage pipeline for training robot policies that generalize across behaviors and environments through neural trajectories - synthetic robot data generated from video …

Video Generation

Learning Real-World Robot Policies by Dreaming

2018-05-20 · AJ Piergiovanni, Alan Wu, Michael S. Ryoo

Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Morphology-Consistent Humanoid Interaction through Robot-Centric Video Synthesis

2026-03-20 · Weisheng Xu, Jian Li, Yi Gu, Bin Yang 외 arxiv

Equipping humanoid robots with versatile interaction skills typically requires either extensive policy training or explicit human-to-robot motion retargeting. However, learning-based policies face prohibitive data collec…

Video Generation Pose Estimation