Inductive logic programming at 30

Cropper, Andrew; Dumančić, Sebastijan; Evans, Richard; Muggleton, Stephen H.

doi:10.48550/arxiv.2102.10556

Cited by 1 publication

(1 citation statement)

References 74 publications

(185 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In very simplified domains such as family tree reasoning (a common benchmark in the ILP community, or blocks world, it may be reasonable to write down an initial background knowledge theory that is sufficient to support induction of a complete set of predicates and rules. However, the background knowledge is "similar to features used in most forms of ML" (Cropper et al, 2021). Just as deep learning has substantially reduced the need to handcode feature functions for many problems, it is possible that the current reliance on handcoded background knowledge theories is a substantial limitation in learning logical representations for embodied intelligent systems.…”

Section: Limitations and Challengesmentioning

confidence: 99%

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence

Roy¹,

Posner²,

Barfoot³

et al. 2021

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Limitations and Challengesmentioning

confidence: 99%