On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

10 results for “robot-vision”

IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Reportcs.CV

Top 8 robotic vision systems tackled lifelong object recognition challenges.

problem Lifelong learning in robotic vision for varied, dynamic environments.

method Design of a dataset with diverse conditions and rules for evaluation.

result Robotic vision systems improved over time with dynamic object appearances.

lifelong learning robotic vision object recognition dynamic environments illumination

2020-04-26abs ↗pdf ↗

OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learningcs.CV

New dataset and benchmarks for lifelong robotic vision tasks.

problem Challenges in applying computer vision to robots, especially lifelong learning.

method Provided a new lifelong robotic vision dataset and benchmarks.

result Demonstrated the complexity and bottlenecks in lifelong object recognition.

lifelong learning robotic vision computer vision catastrophic forgetting open-set

2019-11-15abs ↗pdf ↗

Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoidcs.LG

Study evaluates robot-vision deep learning safety, proposing countermeasures.

problem Vulnerability of robot-vision systems to adversarial examples.

method Empirical analysis and computationally efficient countermeasure.

result Deep networks violate smoothness assumption, making them vulnerable to adversarial examples.

robot-vision deep learning adversarial examples countermeasure smoothness assumption

2017-08-23abs ↗pdf ↗

Multimodal Deep Domain Adaptationcs.LG

Project aims to improve robot vision by adapting to new environments.

problem Robots struggle to recognize objects in new settings.

method Selected and evaluated state-of-the-art DA methods on various datasets.

result Training a good object classifier remains challenging.

robot vision domain adaptation deep learning object recognition multi-modal

2018-07-31abs ↗pdf ↗

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batchescs.LG

Paper introduces rehearsal-free continual learning for small, non-i.i.d. batches in robotic vision.

problem Learning new objects and improving recognition in a changing robotic environment.

method Two rehearsal-free continual learning techniques (CWR* and AR1*) for small, non-i.i.d. batches.

result AR1* outperforms other techniques by more than 15% in some cases.

continual learning rehearsal-free non-i.i.d. batches robotic vision object recognition

2019-07-08abs ↗pdf ↗

Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generationcs.LG

Hierarchical Foresight improves robot vision tasks by planning long-term goals.

problem Compounding uncertainty and scalability issues in long horizon video prediction.

method Subgoal generation and planning using hierarchical visual foresight (HVF).

result Achieves nearly 200% performance improvement in vision-based manipulation tasks.

robotics vision-based tasks long horizon planning subgoal generation self-supervised learning

2019-09-12abs ↗pdf ↗

Challenges in Visual Anomaly Detection for Mobile Robotscs.CV

Detects anomalies in autonomous mobile robots using vision.

problem Anomaly detection for autonomous mobile robots.

method Unsupervised deep learning methods and a novel dataset.

result State-of-the-art approach tested on a new dataset.

Anomaly detection Mobile robots Vision Deep learning Unsupervised

2022-09-22abs ↗pdf ↗

Sensing Anomalies as Potential Hazards: Datasets and Benchmarkscs.RO

Study detects anomalies in robot vision data to predict hazards.

problem Detecting unexpected hazards in robot exploration data.

method Anomaly detection using autoencoders at different scales.

result Autoencoders improve anomaly detection performance on diverse robot scenarios.

robotics anomaly detection autoencoders visual sensing hazard prediction

2021-10-27abs ↗pdf ↗

Geometric algebra and singularities of ruled and developable surfacesmath.DG

Classifies singularities of ruled and developable surfaces using geometric algebra.

problem Characterizing singularities of ruled and developable surfaces.

method Combining dual quaternion algebra and Singularity Theory.

result Local topological type of singular developable surfaces determined by dual torsion vanishing order.

geometric algebra singularities ruled surfaces developable surfaces dual quaternions

2018-08-31abs ↗pdf ↗

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networksstat.ML

This paper optimizes deep neural networks for resource-constrained devices.

problem Efficient deployment of deep neural networks on resource-constrained devices.

method Across-stack optimization of CNNs using weight pruning, channel pruning, quantization, and parallel execution.

result Comprehensive Pareto curves for trade-offs between accuracy, execution time, and memory space.

Deep Learning Neural Networks Optimization Edge Devices Resource Constraints

2018-09-19abs ↗pdf ↗