On the prospects of incorporating large language models (llms) in automated planning and scheduling (aps)
Abstract Automated Planning and Scheduling is among the growing areas in Artificial
Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive …
Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive …
Unsupervised grounding of plannable first-order logic representation from images
M Asai - Proceedings of the International Conference on …, 2019 - aaai.org
Recently, there is an increasing interest in obtaining the relational structures of the
environment in the Reinforcement Learning community. However, the resulting “relations” …
environment in the Reinforcement Learning community. However, the resulting “relations” …
Classical planning in deep latent space
Current domain-independent, classical planners require symbolic models of the problem
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …
Self-supervised learning of scene-graph representations for robotic sequential manipulation planning
We present a self-supervised representation learning approach for visual reasoning and
integrate it into a nonlinear program formulation for motion optimization to tackle sequential …
integrate it into a nonlinear program formulation for motion optimization to tackle sequential …
Consistent scene graph generation by constraint optimization
Scene graph generation takes an image and derives a graph representation of key objects
in the image and their relations. This core computer vision task is often used in autonomous …
in the image and their relations. This core computer vision task is often used in autonomous …
Formalizing consistency and coherence of representation learning
In the study of reasoning in neural networks, recent efforts have sought to improve
consistency and coherence of sequence models, leading to important developments in the …
consistency and coherence of sequence models, leading to important developments in the …
[PDF][PDF] Formalizing Coherence and Consistency Applied to Transfer Learning in Neuro-Symbolic Autoencoders
H Stromfelt, L Dickens, A Garcez… - Advances in Neural …, 2022 - discovery.ucl.ac.uk
In the study of reasoning in neural networks, recent efforts have sought to improve 1
coherence and consistency of neural sequence models. This is an important de-2 velopment …
coherence and consistency of neural sequence models. This is an important de-2 velopment …
Classical planning in deep latent space
Current domain-independent, classical planners require symbolic models of the problem
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …
domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile …
Fully automatic data collection for neuro-symbolic task planning for mobile robot navigation
In this paper, we present an automatic collection method of image data for neuro-symbolic
task planning for robot navigation. Collecting images for robot task planning would often be …
task planning for robot navigation. Collecting images for robot task planning would often be …
Symbolic Reasoning in Latent Space: Classical Planning as an Example
Symbolic systems require hand-coded symbolic representation as input, resulting in a
knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved …
knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved …