Related papers: Learning to Abstract Visuomotor Mappings using Met…
A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific…
Multi-agent reinforcement learning (MARL) is increasingly ubiquitous in training dynamic and adaptive synthetic characters for interactive simulations on geo-specific terrains. Frameworks such as Unity's ML-Agents help to make such…
In this paper we explore the bi-directional mapping between images and their sentence-based descriptions. We propose learning this mapping using a recurrent neural network. Unlike previous approaches that map both sentences and images to a…
Autonomous navigation in complex and partially observable environments remains a central challenge in robotics. Several bio-inspired models of mapping and navigation based on place cells in the mammalian hippocampus have been proposed. This…
How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we search cabinets near the coffee machine and…
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…
Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…
A person's demonstration often serves as a key reference for others learning the same task. However, RGB video, the dominant medium for representing these demonstrations, often fails to capture fine-grained contextual cues such as intent,…
Multi-agent neural implicit mapping allows robots to collaboratively capture and reconstruct complex environments with high fidelity. However, existing approaches often rely on synchronous communication, which is impractical in real-world…
Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited. A fundamental challenge in meta-learning is how to…
Navigation to multiple cued reward locations has been increasingly used to study rodent learning. Though deep reinforcement learning agents have been shown to be able to learn the task, they are not biologically plausible. Biologically…
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…
Achieving reliable multidimensional Vehicle-to-Vehicle (V2V) channel state information (CSI) prediction is both challenging and crucial for optimizing downstream tasks that depend on instantaneous CSI. This work extends traditional…
Training a reinforcement learning agent to carry out natural language instructions is limited by the available supervision, i.e. knowing when the instruction has been carried out. We adapt the CLEVR visual question answering dataset to…
Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation. While recent advances in end-to-end Machine Learning, especially Imitation and Reinforcement Learning…
Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the…
This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN)…
An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero-shot), based on its relationship to previous tasks. Humans can exhibit this cognitive flexibility. By contrast, models that…
Predicting agents' future trajectories plays a crucial role in modern AI systems, yet it is challenging due to intricate interactions exhibited in multi-agent systems, especially when it comes to collision avoidance. To address this…
Cognitive maps are a proposed concept on how the brain efficiently organizes memories and retrieves context out of them. The entorhinal-hippocampal complex is heavily involved in episodic and relational memory processing, as well as spatial…