From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
arXiv:2110.15245
Abstract
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning methods to a particular problem set has become an established and valuable modus operandi to advance a particular field. In this article we argue that such an approach does not straightforwardly extended to robotics -- or to embodied intelligence more generally: systems which engage in a purposeful exchange of energy and information with a physical environment. In particular, the purview of embodied intelligent agents extends significantly beyond the typical considerations of main-stream machine learning approaches, which typically (i) do not consider operation under conditions significantly different from those encountered during training; (ii) do not consider the often substantial, long-lasting and potentially safety-critical nature of interactions during learning and deployment; (iii) do not require ready adaptation to novel tasks while at the same time (iv) effectively and efficiently curating and extending their models of the world through targeted and deliberate actions. In reality, therefore, these limitations result in learning-based systems which suffer from many of the same operational shortcomings as more traditional, engineering-based approaches when deployed on a robot outside a well defined, and often narrow operating envelope. Contrary to viewing embodied intelligence as another application domain for machine learning, here we argue that it is in fact a key driver for the advancement of machine learning technology. In this article our goal is to highlight challenges and opportunities that are specific to embodied intelligence and to propose research directions which may significantly advance the state-of-the-art in robot learning.
References in corpus (39)
- Auto-Encoding Variational Bayes
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
- Towards a Definition of Disentangled Representations
- Data-Efficient Hierarchical Reinforcement Learning
- A Flexible and Robust Large Scale Capacitive Tactile System for Robots
- MONet: Unsupervised Scene Decomposition and Representation
- Learning Symbolic Models of Stochastic Domains
- Learning Discrete Structures for Graph Neural Networks
- Variational Intrinsic Control
- GMNN: Graph Markov Neural Networks
- Argoverse: 3D Tracking and Forecasting with Rich Maps
- FFRob: Leveraging Symbolic Planning for Efficient Task and Motion Planning
- Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
- GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
- A PAC-Bayesian bound for Lifelong Learning
- BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
- The Consciousness Prior
- Symbol Emergence in Cognitive Developmental Systems: a Survey
- Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
- Continual Unsupervised Representation Learning
- Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
- Surprisingly Robust In-Hand Manipulation: An Empirical Study
- Neural Logic Machines
- Sim2Real View Invariant Visual Servoing by Recurrent Control
- iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes
- SCALOR: Generative World Models with Scalable Object Representations
- Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
- Neural Relational Inference with Fast Modular Meta-learning
- Systematic Generalization: What Is Required and Can It Be Learned?
- Towards causal generative scene models via competition of experts
- Unsupervised Grounding of Plannable First-Order Logic Representation from Images
- Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
- Coordination Among Neural Modules Through a Shared Global Workspace
- Compositionality decomposed: how do neural networks generalise?
- Dropout Distillation for Efficiently Estimating Model Confidence
- Discrete-Valued Neural Communication
- SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning