In this paper, we introduce a method for unifying language, action, and ...
We address the challenging problem of open world object detection (OWOD)...
Neural Radiance Fields (NeRFs) learn implicit representations of - typic...
Skill-based reinforcement learning (RL) has emerged as a promising strat...
We show that ensembling effectively quantifies model uncertainty in Neur...
Modelling individual objects as Neural Radiance Fields (NeRFs) within a
...
We introduce powerful ideas from Hyperdimensional Computing into the
cha...
While deep reinforcement learning (RL) agents have demonstrated incredib...
Recent Semantic SLAM methods combine classical geometry-based estimation...
We present the design and implementation of a taskable reactive mobile
m...
Semantic segmentation is an important task that helps autonomous vehicle...
We present Bayesian Controller Fusion (BCF): a hybrid control strategy t...
Visual localization techniques often comprise a hierarchical localizatio...
Deployed into an open world, object detectors are prone to a type of fal...
For robots to navigate and interact more richly with the world around th...
Do you want to improve 1.0 AP for your object detector without any infer...
Post-deployment, an object detector is expected to operate at a similar ...
Performance monitoring of object detection is crucial for safety-critica...
Being able to explore an environment and understand the location and typ...
Accurately ranking a huge number of candidate detections is a key to the...
We introduce BenchBot, a novel software suite for benchmarking the
perfo...
Existing open set classifiers distinguish between known and unknown inpu...
Learning-based approaches often outperform hand-coded algorithmic soluti...
The computer vision and robotics research communities are each strong.
H...
In this work we focus on improving the efficiency and generalisation of
...
Emerging object-based SLAM algorithms can build a graph representation o...
We introduce a new challenge for computer and robotic vision, the first ...
Object detection is an integral part of an autonomous vehicle for its
sa...
We propose a new visual object detector evaluation measure which not onl...
Current end-to-end Reinforcement Learning (RL) approaches are severely
l...
Current approaches to object-oriented SLAM lack the ability to incorpora...
There has been a recent emergence of sampling-based techniques for estim...
Model-free reinforcement learning has recently been shown to be effectiv...
The application of deep learning in robotics leads to very specific prob...
Research in Simultaneous Localization And Mapping (SLAM) is increasingly...
A robot that can carry out a natural-language instruction has been a dre...
Dropout Variational Inference, or Dropout Sampling, has been recently
pr...
This paper presents SceneCut, a novel approach to jointly discover previ...
Trip hazards are a significant contributor to accidents on construction ...
We investigate different strategies for active learning with Bayesian de...
The success of deep learning techniques in the computer vision domain ha...
After the incredible success of deep learning in the computer vision dom...