[论文解读] World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges

Tadahiro Taniguchi, Shingo Murata+9 more|arXiv (Cornell University)|Jan 14, 2023

Computability, Logic, AI Algorithms被引用 6

一句话总结

本综述论文将世界模型与预测编码整合于认知与发育机器人学中，提出这些框架可通过感知运动交互实现终身、具身化学习。论文识别出潜在表征、神经符号整合与行为涌现等方面的关键挑战，并主张采用类脑架构以实现机器人真正的认知发展。

ABSTRACT

Creating autonomous robots that can actively explore the environment, acquire knowledge and learn skills continuously is the ultimate achievement envisioned in cognitive and developmental robotics. Their learning processes should be based on interactions with their physical and social world in the manner of human learning and cognitive development. Based on this context, in this paper, we focus on the two concepts of world models and predictive coding. Recently, world models have attracted renewed attention as a topic of considerable interest in artificial intelligence. Cognitive systems learn world models to better predict future sensory observations and optimize their policies, i.e., controllers. Alternatively, in neuroscience, predictive coding proposes that the brain continuously predicts its inputs and adapts to model its own dynamics and control behavior in its environment. Both ideas may be considered as underpinning the cognitive development of robots and humans capable of continual or lifelong learning. Although many studies have been conducted on predictive coding in cognitive robotics and neurorobotics, the relationship between world model-based approaches in AI and predictive coding in robotics has rarely been discussed. Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics. Furthermore, we outline the frontiers and challenges involved in world models and predictive coding toward the further integration of AI and robotics, as well as the creation of robots with real cognitive and developmental capabilities in the future.

研究动机与目标

• 阐明世界模型、预测编码、自由能原理（FEP）与主动推断在认知与发育机器人学中的定义及其相互关系。
• 识别当前世界模型与预测编码方法在机器人学中面临的关键研究空白。
• 探讨这些框架如何通过具身化、感知运动交互支持持续的终身学习。
• 考察认知架构中高维感官输入、离散与连续动作以及社会交互的整合方式。
• 解决行为涌现、数据效率与类脑设计等根本性挑战，以推动通用人工智能的发展。

提出的方法

• 本文对人工智能与机器人学中世界模型与预测编码进行了全面综述，重点关注其理论与实证基础。
• 梳理了世界模型、预测编码、FEP与主动推断之间的概念关系，强调其在预测与误差最小化方面共享的机制。
• 分析了用于构建内部世界模型的深度生成模型、自编码器与循环网络等前沿方法。
• 评估了当前机器人实现中在数据效率、动作规划与动态环境适应性方面的表现。
• 提出了一种整合神经符号表征与可及性感知的框架，以增强机器人认知发展。
• 倡导采用类脑架构，将预测编码与形态计算及主动感知相结合。

实验结果

研究问题

• RQ1 在认知与发育机器人学的语境下，世界模型与预测编码之间有何关系？
• RQ2 基于世界模型与预测编码构建数据高效、终身学习系统的关键挑战是什么？
• RQ3 世界模型如何通过身体-环境交互支持复杂行为的涌现？
• RQ4 神经符号整合与可及性感知在何种方式下可增强发育机器人的认知能力？
• RQ5 类脑架构与自由能原理如何指导真正具备认知与发育能力的机器人系统的设计？

主要发现

• 机器人中的世界模型并非环境的客观表征，而是基于感知运动经验构建的主观、以智能体为中心的模型，类似于‘环境感知’（Umwelt）概念。
• 预测编码为感知与行动提供了一个统一框架，即大脑或智能体通过最小化预测误差来优化行为与模型准确性。
• 当前人工智能中的世界模型方法数据需求量大，缺乏人类发展所展现的数据效率，限制了其在终身学习中的应用。
• 将世界模型与主动推断及自由能原理相结合，可使机器人以生物学上合理的方式通过预测、行动与误差校正实现学习。
• 诸如被动行走等涌现行为，源于身体与环境的交互，而无需显式的世界模型，这挑战了所有行为均需内部模型的必要性。
• 关键前沿包括开发神经符号预测模型、实现社会交互学习，以及设计支持持续发展的类脑认知架构。