Related papers: Learning Continuous Environment Fields via Implici…
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…
We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of…
The pipeline of current robotic pick-and-place methods typically consists of several stages: grasp pose detection, finding inverse kinematic solutions for the detected poses, planning a collision-free trajectory, and then executing the…
Recent advances have enabled a single neural network to serve as an implicit scene representation, establishing the mapping function between spatial coordinates and scene properties. In this paper, we make a further step towards continual…
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in…
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…
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…
Implicit representations of 3D objects have recently achieved impressive results on learning-based 3D reconstruction tasks. While existing works use simple texture models to represent object appearance, photo-realistic image synthesis…
Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. However, these models typically require manual and careful human data collection for training. In this paper, we…
Implicit fields have recently shown increasing success in representing and learning 3D shapes accurately. Signed distance fields and occupancy fields are decades old and still the preferred representations, both with well-studied…
Object goal navigation aims to navigate an agent to locations of a given object category in unseen environments. Classical methods explicitly build maps of environments and require extensive engineering while lacking semantic information…
Object Goal Navigation (ObjectNav) task is to navigate an agent to an object category in unseen environments without a pre-built map. In this paper, we solve this task by predicting the distance to the target using semantically-related…
Predicting an agent's future trajectory is a challenging task given the complicated stimuli (environmental/inertial/social) of motion. Prior works learn individual stimulus from different modules and fuse the representations in an…
Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…
We consider the problem of object goal navigation in unseen environments. Solving this problem requires learning of contextual semantic priors, a challenging endeavour given the spatial and semantic variability of indoor environments.…
Predicting the motion of a mobile agent from a third-person perspective is an important component for many robotics applications, such as autonomous navigation and tracking. With accurate motion prediction of other agents, robots can plan…
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…
This work proposes a novel method for estimating the influence that unknown static objects might have over mobile agents. Since the motion of agents can be affected by the presence of fixed objects, it is possible use the information about…
Human movement is goal-directed and influenced by the spatial layout of the objects in the scene. To plan future human motion, it is crucial to perceive the environment -- imagine how hard it is to navigate a new room with lights off.…
We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding. Unlike prior methods that rely on discrete tracking or view-dependent features, our approach disentangles…