Related papers: Static force field representation of environments …
Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from…
Formation strategy is one of the most important parts of many multi-agent systems with many applications in real world problems. In this paper, a framework for learning this task in a limited domain (restricted environment) is proposed. In…
Multi-agent trajectory prediction is a fundamental problem in autonomous driving. The key challenges in prediction are accurately anticipating the behavior of surrounding agents and understanding the scene context. To address these…
In multi-agent reinforcement learning, the inherent non-stationarity of the environment caused by other agents' actions posed significant difficulties for an agent to learn a good policy independently. One way to deal with non-stationarity…
Learning and adaptation play great role in emergent socio-economic phenomena. Complex dynamics has been previously found in the systems of multiple learning agents interacting via a simple game. Meanwhile, the single agent adaptation is…
Intelligent agents gather information and perceive semantics within the environments before taking on given tasks. The agents store the collected information in the form of environment models that compactly represent the surrounding…
Movement is how people interact with and affect their environment. For realistic character animation, it is necessary to synthesize such interactions between virtual characters and their surroundings. Despite recent progress in character…
We propose Occupancy Flow Fields, a new representation for motion forecasting of multiple agents, an important task in autonomous driving. Our representation is a spatio-temporal grid with each grid cell containing both the probability of…
The state of a classical point-particle system may often be specified by giving the position and momentum for each constituent particle. For non-pointlike particles, the center-of-mass position may be augmented by an additional coordinate…
Predicting future locations of agents in the scene is an important problem in self-driving. In recent years, there has been a significant progress in representing the scene and the agents in it. The interactions of agents with the scene and…
In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis. We model human actions using the topological features of the attractor of the dynamical system.…
Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving. Most existing works exploit static road graphs to characterize scenarios and are limited in modeling…
Agent-based modelling is a valuable approach for systems whose behaviour is driven by the interactions between distinct entities. They have shown particular promise as a means of modelling crowds of people in streets, public transport…
We present a new model for multi-agent dynamics where each agent is described by its position and body attitude: agents travel at a constant speed in a given direction and their body can rotate around it adopting different configurations.…
Learning in multi-agent environments is difficult due to the non-stationarity introduced by an opponent's or partner's changing behaviors. Instead of reactively adapting to the other agent's (opponent or partner) behavior, we propose an…
Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel approach for scene understanding, leveraging a hierarchical…
Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…
We address the problem of active mapping with a continually-learned neural scene representation, namely Active Neural Mapping. The key lies in actively finding the target space to be explored with efficient agent movement, thus minimizing…
We describe a method for performing active localization of objects in instances of visual situations. A visual situation is an abstract concept---e.g., "a boxing match", "a birthday party", "walking the dog", "waiting for a bus"---whose…
In this paper, we analyze the behavior of a multi-agent system driven by the interactions of agents within a competitive environment. To achieve this, we describe the transition probabilities that underlie the system's stochastic nature. We…