Related papers: Learning Neuro-Symbolic Relational Transition Mode…

Learned Neural Network based policies have shown promising results for robot navigation. However, most of these approaches fall short of being used on a real robot due to the extensive simulated training they require. These simulations lack…

This article proposes a biologically inspired neurocomputational architecture which learns associations between words and referents in different contexts, considering evidence collected from the literature of Psycholinguistics and…

In recent years, there has been an increase in using deep learning for climate and weather modeling. Though results have been impressive, explainability and interpretability of deep learning models are still a challenge. A third wave of…

As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…

Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models that…

Continual learning is crucial for creating AI agents that can learn and improve themselves autonomously. A primary challenge in continual learning is to learn new tasks without losing previously learned knowledge. Current continual learning…

Mental rotation -- the ability to compare objects seen from different viewpoints -- is a fundamental example of mental simulation and spatial world modeling in humans. Here we propose a mechanistic model of human mental rotation, leveraging…

Recurrent Neural Networks (RNNs) can encode rich dynamics which makes them suitable for modeling dynamic systems. To train an RNN for multi-step prediction of dynamic systems, it is crucial to efficiently address the state initialization…

Our goal is to enable a robot to learn how to sequence its actions to perform tasks specified as natural language instructions, given successful demonstrations from a human partner. The ability to plan high-level tasks can be factored as…

Trajectory planning in robotics is understood as generating a sequence of joint configurations that will lead a robotic agent, or its manipulator, from an initial state to the desired final state, thus completing a manipulation task while…

Crash simulations play an essential role in improving vehicle safety, design optimization, and injury risk estimation. Unfortunately, numerical solutions of such problems using state-of-the-art high-fidelity models require significant…

For social robots to be brought more into widespread use in the fields of companionship, care taking and domestic help, they must be capable of demonstrating social intelligence. In order to be acceptable, they must exhibit…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

Teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments is a challenging problem. We consider that user defines every task by a linear temporal logic (LTL) formula. However, some causal…

Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…

We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive robot states, and…

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind…

Neural models and symbolic algorithms have recently been combined for tasks requiring both perception and reasoning. Neural models ground perceptual input into a conceptual vocabulary, on which a classical reasoning algorithm is applied to…

Robots will be expected to manipulate a wide variety of objects in complex and arbitrary ways as they become more widely used in human environments. As such, the rearrangement of objects has been noted to be an important benchmark for AI…

Despite the growing interest in robot control utilizing the computation of biological neurons, context-dependent behavior by neuron-connected robots remains a challenge. Context-dependent behavior here is defined as behavior that is not the…