5 papers
Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki +2
Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning. Despite its successes, important limitations rema…
What Can Eye Gaze Teach Us About Real-World Cycling? Insights From the Oxford RobotCycle Project
Benjamin Hardin, Efimia Panagiotaki, Daniele De Martini +1
Although much is known about the physical danger of cycling situations, less is understood about the perceived danger of cycling. Furthermore, perception of danger may be filtered…
Introspection in Learned Semantic Scene Graph Localisation
Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini
This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a l…
NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms
Efimia Panagiotaki, Daniele De Martini, Lars Kunze +2
This study explores the intersection of neural networks and classical robotics algorithms through the Neural Algorithmic Reasoning (NAR) blueprint, enabling the training of neural…
GraphSCENE: On-Demand Critical Scenario Generation for Autonomous Vehicles in Simulation
Efimia Panagiotaki, Georgi Pramatarov, Lars Kunze +1
Testing and validating Autonomous Vehicle (AV) performance in safety-critical and diverse scenarios is crucial before real-world deployment. However, manually creating such scenari…