10 papers
Towards a Causal Probabilistic Framework for Prediction, Action-Selection & Explanations for Robot Block-Stacking Tasks
Ricardo Cannizzaro, Jonathan Routley, Lars Kunze
Uncertainties in the real world mean that is impossible for system designers to anticipate and explicitly design for all scenarios that a robot might encounter. Thus, robots design…
CC-SGG: Corner Case Scenario Generation using Learned Scene Graphs
George Drayson, Efimia Panagiotaki, Daniel Omeiza +1
Corner case scenarios are an essential tool for testing and validating the safety of autonomous vehicles (AVs). As these scenarios are often insufficiently present in naturalistic…
Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models
Efimia Panagiotaki, Daniele De Martini, Lars Kunze
In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Graph Deep Learning…
SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention
Efimia Panagiotaki, Daniele De Martini, Georgi Pramatarov +2
This paper proposes a Graph Neural Network(GNN)-based method for exploiting semantics and local geometry to guide the identification of reliable pointcloud registration candidates.…
CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments
Ricardo Cannizzaro, Lars Kunze
Robots operating in real-world environments must reason about possible outcomes of stochastic actions and make decisions based on partial observations of the true world state. A ma…
LiDAR Lateral Localisation Despite Challenging Occlusion from Traffic
Tarlan Suleymanov, Matthew Gadd, Lars Kunze +1
This paper presents a system for improving the robustness of LiDAR lateral localisation systems. This is made possible by including detections of road boundaries which are invisibl…