Related papers: Open-ended search for environments and adapted age…
Autonomous driving perceives surroundings with line-of-sight sensors that are compromised under environmental uncertainties. To achieve real time global information in high definition map, we investigate to share perception information…
Natural lifeforms specialise to their environmental niches across many levels; from low-level features such as DNA and proteins, through to higher-level artefacts including eyes, limbs, and overarching body plans. We propose Multi-Level…
Evaluating the general abilities of intelligent agents requires complex simulation environments. Existing benchmarks typically evaluate only one narrow task per environment, requiring researchers to perform expensive training runs on many…
Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…
To perform tasks well in a new domain, one must first know something about it. This paper reports on a robot controller for navigation through unfamiliar indoor worlds. Based on spatial affordances, it integrates planning with reactive…
Developing agents capable of autonomously interacting with complex and dynamic environments, where task structures may change over time and prior knowledge cannot be relied upon, is a key prerequisite for deploying artificial systems in…
Recent advances in deep reinforcement learning (RL) have demonstrated complex decision-making capabilities in simulation environments such as Arcade Learning Environment, MuJoCo, and ViZDoom. However, they are hardly extensible to more…
In the pursuit of artificial general intelligence, our most significant measurement of progress is an agent's ability to achieve goals in a wide range of environments. Existing platforms for constructing such environments are typically…
While fields like Artificial Life have made huge strides in quantifying the mechanisms that distinguish living systems from non-living ones, particular mechanisms remain difficult to reproduce in silico. Known as open-endedness, we've been…
This paper introduces EvoCraft, a framework for Minecraft designed to study open-ended algorithms. We introduce an API that provides an open-source Python interface for communicating with Minecraft to place and track blocks. In contrast to…
Advances in artificial intelligence often stem from the development of new environments that abstract real-world situations into a form where research can be done conveniently. This paper contributes such an environment based on ideas…
In this paper we propose a novel architecture, CARD, for resource discovery in large scale Mobile Ad hoc Networks (MANets) which, may scale up to thousands of nodes and may span wide geographical regions. Unlike previously proposed schemes,…
Existing exploration algorithms mainly generate frontiers using random sampling or motion primitive methods within a specific sensor range or search space. However, frontiers generated within constrained spaces lead to back-and-forth…
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are…
Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller. Evolutionary algorithms (EAs), combined with physical simulators, represent a valid tool to overcome this issue. In this…
Autonomous exploration of multi-floor buildings remains challenging for ground robots because conventional 2D and 2.5D maps cannot represent overlapping traversable surfaces such as stairs, ramps, and multiple reachable elevations. This…
We introduce Nomad, a system for autonomous data exploration and insight discovery. Given a corpus of documents, databases, or other data sources, users rarely know the full set of questions, hypotheses, or connections that could be…
We present PACE, a novel method for modifying motion-captured virtual agents to interact with and move throughout dense, cluttered 3D scenes. Our approach changes a given motion sequence of a virtual agent as needed to adjust to the…
Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate generalization, exploration should be task agnostic; 2) to…
We address planning and navigation in challenging 3D video games featuring maps with disconnected regions reachable by agents using special actions. In this setting, classical symbolic planners are not applicable or difficult to adapt. We…