Search Results for author:
Found 38 papers, 14 papers with code
Addressing the Challenges of Open-World Object Detection
We address the challenging problem of open world object detection (OWOD), where object detectors must identify objects from known classes while also identifying and continually learning to detect novel objects.
ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fields
ParticleNeRF is the first online dynamic NeRF and achieves fast adaptability with better visual fidelity than brute-force online InstantNGP and other baseline approaches on dynamic scenes with online constraints.
Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics
Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space.
Retrospectives on the Embodied AI Workshop
We present a retrospective on the state of Embodied AI research.
Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields
We show that ensembling effectively quantifies model uncertainty in Neural Radiance Fields (NeRFs) if a density-aware epistemic uncertainty term is considered.
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
We address the problem of out-of-distribution (OOD) detection for the task of object detection.
Hyperdimensional Feature Fusion for Out-Of-Distribution Detection
We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots
While deep reinforcement learning (RL) agents have demonstrated incredible potential in attaining dexterous behaviours for robotics, they tend to make errors when deployed in the real world due to mismatches between the training and execution environments.
FSNet: A Failure Detection Framework for Semantic Segmentation
Semantic segmentation is an important task that helps autonomous vehicles understand their surroundings and navigate safely.
Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics
More importantly, given the risk-aversity of the control prior, BCF ensures safe exploration and deployment, where the control prior naturally dominates the action distribution in states unknown to the policy.
Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness
Probabilistic state-estimation approaches offer a principled foundation for designing localization systems, because they naturally integrate sequences of imperfect motion and exteroceptive sensor data.
Probabilistic Visual Place Recognition for Hierarchical Localization
In this letter, we propose two methods which adapt image retrieval techniques used for visual place recognition to the Bayesian state estimation formulation for localization.
Uncertainty for Identifying Open-Set Errors in Visual Object Detection
We also introduce a methodology for converting existing object detection datasets into specific open-set datasets to evaluate open-set performance in object detection.
Semantics for Robotic Mapping, Perception and Interaction: A Survey
In robotics and related research fields, the study of understanding is often referred to as semantics, which dictates what does the world "mean" to a robot, and is strongly tied to the question of how to represent that meaning.
SWA Object Detection
In this technique report, we systematically investigate the effects of applying SWA to object detection as well as instance segmentation.
Online Monitoring of Object Detection Performance During Deployment
During deployment, an object detector is expected to operate at a similar performance level reported on its testing dataset.
Per-frame mAP Prediction for Continuous Performance Monitoring of Object Detection During Deployment
Performance monitoring of object detection is crucial for safety-critical applications such as autonomous vehicles that operate under varying and complex environmental conditions.
VarifocalNet: An IoU-aware Dense Object Detector
In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy.
BenchBot: Evaluating Robotics Research in Photorealistic 3D Simulation and on Real Robots
We introduce BenchBot, a novel software suite for benchmarking the performance of robotics research across both photorealistic 3D simulations and real robot platforms.
Robotics
Class Anchor Clustering: a Loss for Distance-based Open Set Recognition
We also show that our anchored class centres achieve higher open set performance than learnt class centres, particularly on object-based datasets and large numbers of training classes.
Multiplicative Controller Fusion: Leveraging Algorithmic Priors for Sample-efficient Reinforcement Learning and Safe Sim-To-Real Transfer
We present a novel approach to model-free reinforcement learning that can leverage existing sub-optimal solutions as an algorithmic prior during training and deployment.
What can robotics research learn from computer vision research?
The computer vision and robotics research communities are each strong.
Residual Reactive Navigation: Combining Classical and Learned Navigation Strategies For Deployment in Unknown Environments
In this work we focus on improving the efficiency and generalisation of learned navigation strategies when transferred from its training environment to previously unseen ones.
Where are the Keys? -- Learning Object-Centric Navigation Policies on Semantic Maps with Graph Convolutional Networks
Emerging object-based SLAM algorithms can build a graph representation of an environment comprising nodes for robot poses and object landmarks.
The Probabilistic Object Detection Challenge
We introduce a new challenge for computer and robotic vision, the first ACRV Robotic Vision Challenge, Probabilistic Object Detection.
Did You Miss the Sign? A False Negative Alarm System for Traffic Sign Detectors
The proposed method raises an alarm when it discovers a failure by the object detector to detect a traffic sign.
Probabilistic Object Detection: Definition and Evaluation
We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections.
Sim-to-Real Transfer of Robot Learning with Variable Length Inputs
Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating prior knowledge.
Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks.
The Limits and Potentials of Deep Learning for Robotics
In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning.
Robotics
QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM
In this paper, we use 2D object detections from multiple views to simultaneously estimate a 3D quadric surface for each object and localize the camera position.
Robotics
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering.
Ranked #3 on
Visual Navigation
on R2R
Dropout Sampling for Robust Object Detection in Open-Set Conditions
Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks.
SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image.
Multi-Modal Trip Hazard Affordance Detection On Construction Sites
Trip hazards are a significant contributor to accidents on construction and manufacturing sites, where over a third of Australian workplace injuries occur [1].
Episode-Based Active Learning with Bayesian Neural Networks
We investigate different strategies for active learning with Bayesian deep neural networks.
Meaningful Maps With Object-Oriented Semantic Mapping
For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them.
Robotics
On the Performance of ConvNet Features for Place Recognition
Computer vision datasets are very different in character to robotic camera data, real-time performance is essential, and performance priorities can be different.
