Related papers: Memory-Augmented Reinforcement Learning for Image-…
Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their…
The idea of using the recurrent neural network for visual attention has gained popularity in computer vision community. Although the recurrent attention model (RAM) leverages the glimpses with more large patch size to increasing its scope,…
Understanding and mapping a new environment are core abilities of any autonomously navigating agent. While classical robotics usually estimates maps in a stand-alone manner with SLAM variants, which maintain a topological or metric…
Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While these generalization capabilities to an unknown environment…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
Object Goal Navigation requires a robot to find and navigate to an instance of a target object class in a previously unseen environment. Our framework incrementally builds a semantic map of the environment over time, and then repeatedly…
This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space…
Embodied artificial intelligence (AI) tasks shift from tasks focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments. In this paper, we investigate the target-driven visual…
Autonomous navigation is an essential capability of smart mobility for mobile robots. Traditional methods must have the environment map to plan a collision-free path in workspace. Deep reinforcement learning (DRL) is a promising technique…
In recent years, learning-based approaches have demonstrated significant promise in addressing intricate navigation tasks. Traditional methods for training deep neural network navigation policies rely on meticulously designed reward…
Image goal navigation requires two different skills: firstly, core navigation skills, including the detection of free space and obstacles, and taking decisions based on an internal representation; and secondly, computing directional…
We introduce a learning-based approach for room navigation using semantic maps. Our proposed architecture learns to predict top-down belief maps of regions that lie beyond the agent's field of view while modeling architectural and stylistic…
Vision and voice are two vital keys for agents' interaction and learning. In this paper, we present a novel indoor navigation model called Memory Vision-Voice Indoor Navigation (MVV-IN), which receives voice commands and analyzes multimodal…
In self driving car applications, there is a requirement to predict the location of the lane given an input RGB front facing image. In this paper, we propose an architecture that allows us to increase the speed and robustness of road…
Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…
Deep learning based computer vision fails to work when labeled images are scarce. Recently, Meta learning algorithm has been confirmed as a promising way to improve the ability of learning from few images for computer vision. However,…
Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense and spatial reasoning for efficient exploration in…
The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…
In this paper, we propose a novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.…
This paper presents a reinforcement learning method for object goal navigation (ObjNav) where an agent navigates in 3D indoor environments to reach a target object based on long-term observations of objects and scenes. To this end, we…