Related papers: Hierarchical Active Inference using Successor Repr…

The sudden appearance of occluded pedestrians presents a critical safety challenge in autonomous driving. Conventional rule-based or purely data-driven approaches struggle with the inherent high uncertainty of these long-tail scenarios. To…

Rich semantic relations are important in a variety of visual recognition problems. As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene. State of the art…

Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation. However, this framework has yet to provide practical sensorimotor…

We advance a novel computational model of multi-agent, cooperative joint actions that is grounded in the cognitive framework of active inference. The model assumes that to solve a joint task, such as pressing together a red or blue button,…

The hippocampal-entorhinal complex plays a major role in the organization of memory and thought. The formation of and navigation in cognitive maps of arbitrary mental spaces via place and grid cells can serve as a representation of memories…

The human brain possesses the extraordinary capability to contextualize the information it receives from our environment. The entorhinal-hippocampal plays a critical role in this function, as it is deeply engaged in memory processing and…

To make good decisions in the real world people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very useful…

Long horizon sequential manipulation tasks are effectively addressed hierarchically: at a high level of abstraction the planner searches over abstract action sequences, and when a plan is found, lower level motion plans are generated. Such…

We present a categorical formulation of the cognitive frameworks of Predictive Processing and Active Inference, expressed in terms of string diagrams interpreted in a monoidal category with copying and discarding. This includes diagrammatic…

We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes physical and cognitive limitations of the oracle into account when selecting sensor data to be annotated by…

We propose a meta path planning algorithm named \emph{Neural Exploration-Exploitation Trees~(NEXT)} for learning from prior experience for solving new path planning problems in high dimensional continuous state and action spaces. Compared…

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…

Learning precise surrogate models of complex computer simulations and physical machines often require long-lasting or expensive experiments. Furthermore, the modeled physical dependencies exhibit nonlinear and nonstationary behavior.…

To interpret deep neural networks, one main approach is to dissect the visual input and find the prototypical parts responsible for the classification. However, existing methods often ignore the hierarchical relationship between these…

Active inference introduces a theory describing action-perception loops via the minimisation of variational (and expected) free energy or, under simplifying assumptions, (weighted) prediction error. Recently, active inference has been…

This work pushes the boundaries of learning-based methods in autonomous robot exploration in terms of environmental scale and exploration efficiency. We present HEADER, an attention-based reinforcement learning approach with hierarchical…

Large-scale multi-agent pathfinding (MAPF) presents significant challenges in several areas. As systems grow in complexity with a multitude of autonomous agents operating simultaneously, efficient and collision-free coordination becomes…

We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor…

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…

In this paper we present a computational modeling account of an active self in artificial agents. In particular we focus on how an agent can be equipped with a sense of control and how it arises in autonomous situated action and, in turn,…