The field of autonomous navigation and perception is rapidly evolving, with a focus on developing innovative solutions for robust and accurate localization, mapping, and object detection. Recent research has explored the use of topological maps, lidar scan matching, and event-based cameras to improve navigation in complex environments. Additionally, there has been a growing interest in addressing security concerns, such as adversarial attacks and sybil-based attacks, which can compromise the reliability of autonomous systems. Noteworthy papers in this area include PRISM-Loc, which proposes a lightweight long-range lidar localization approach, and Adversarial Attacks and Detection in Visual Place Recognition, which analyzes the effect of adversarial attacks on visual place recognition systems. Another notable work is DepthVanish, which introduces a novel stereo depth attack that jointly optimizes both the striped structure and texture elements.
Advancements in Autonomous Navigation and Perception
Sources
PRISM-Loc: a Lightweight Long-range LiDAR Localization in Urban Environments with Topological Maps
A Low-Cost Portable Lidar-based Mobile Mapping System on an Android Smartphone
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot Navigation
An efficient neuromorphic approach for collision avoidance combining Stack-CNN with event cameras
DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
Orbital Collision: An Indigenously Developed Web-based Space Situational Awareness Platform
LunarLoc: Segment-Based Global Localization on the Moon
The Starlink Robot: A Platform and Dataset for Mobile Satellite Communication
Look to Locate: Vision-Based Multisensory Navigation with 3-D Digital Maps for GNSS-Challenged Environments
Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
On the Impact of Sybil-based Attacks on Mobile Crowdsensing for Transportation
A Computationally Aware Multi Objective Framework for Camera LiDAR Calibration
Joint attitude estimation and 3D neural reconstruction of non-cooperative space objects
Model-Based Real-Time Pose and Sag Estimation of Overhead Power Lines Using LiDAR for Drone Inspection
CURL-SLAM: Continuous and Compact LiDAR Mapping
Generative Adversarial Evasion and Out-of-Distribution Detection for UAV Cyber-Attacks