This is our latest selection of worldwide publications and patents in english on Autonomous Vehicles, between many scientific online journals, classified and focused on autonomous vehicle, self-driving, LIDAR, road mapping, fleet management, navigation algorithm and path planning.
RL-Based Vibration-Aware Path Planning for Mobile Robots’ Health and Safety
Published on 2025-03-10 by Sathian Pookkuttath, Braulio Felix Gomez, Mohan Rajesh Elara @MDPI
Abstract: Mobile robots are widely used, with research focusing on autonomy and functionality. However, long-term deployment requires their health and safety to be ensured. Terrain-induced vibrations accelerate wear. Hence, self-awareness and optimal path selection, avoiding such terrain anomalies, is essential. This study proposes an RL-based vibration-aware path planning framework, incorporating terrain roughness level classification, a vibration cost map, and an optimized vibration-aware path planning [...]
Our summary: Validation through virtual and real-world experiments shows effective avoidance of rough areas while maintaining shortest distance compared to A* algorithm.
RL-Based, Vibration-Aware, Path Planning, Mobile Robots RL-Based Vibration-Aware Path Planning framework incorporates terrain roughness level classification, vibration cost map, and optimized path planning strategy. IMU sensor data classifies terrain roughness, creating a vibration cost map for optimal path selection. RL model with deep RL training adapts to changing terrain for navigation.
Publication
Multi-Flight Path Planning for a Single Agricultural Drone in a Regular Farmland Area
Published on 2025-03-10 by Haohan Dong, Xiaohan Ma, Si Zhang @MDPI
Abstract: The sustainable management of agricultural systems is crucial for ensuring food security and environmental stewardship. This paper advances development in the field of sustainable agriculture by focusing on the application of plant protection drone technology in efficiently controlling crop diseases and pests. This paper investigates multi-flight path planning for a single agricultural drone in regular farmland, establishing a path planning model that takes into account environmental factors and[...]
Our summary: This paper presents a novel multi-flight path planning model for a single agricultural drone in regular farmland, optimizing pesticide and energy consumption. The study introduces an innovative optimization algorithm that dynamically adjusts the cost function of the A* algorithm, resulting in significant enhancements in optimization efficiency. The proposed method aids in reducing energy consumption and enhancing agricultural production efficiency for sustainable development.
multi-flight path planning, agricultural drone, optimization algorithm, sustainable agriculture
Publication
An Experimental and Case Study Approach
Published on 2025-03-07 by Recep Eken, O?uzhan Co?kun, G�ne? Y?lmaz @MDPI
Abstract: LIDAR technology is widely used in autonomous driving and environmental sensing, but its accuracy is significantly affected by variations in vehicle surface reflectivity. This study models and predicts the impact of different LIDAR sensor specifications and vehicle surface paints on laser intensity measurements. Laser intensity data from the experiments of Shung et al. were analyzed alongside vehicle color, angle, and distance. Multiple machine learning models were tested, with Gaussian Process [...]
Our summary: Experimental study modeling impact of LIDAR sensor specs and vehicle surface paints on laser intensity measurements using machine learning. GPR model achieves high accuracy in predicting laser intensity values. Model validated and tested on real-world dataset, showing robustness across different surface reflectivity conditions.
LIDAR, machine learning, laser intensity, surface reflectivity
Publication
Variational Autoencoder for the Prediction of Oil Contamination Temporal Evolution in Water Environments
Published on 2025-03-07 by Alejandro Casado-P�rez, Samuel Yanes, Sergio L. Toral, Manuel Perales-Esteve, Daniel Guti�rrez-Reina @MDPI
Abstract: The water quality monitoring of large water masses using robotic vehicles is a complex task highly developed in recent years. The main approaches utilize adaptative informative path planning of fleets of autonomous surface vehicles and computer learning methods. However, water monitoring is characterized by a highly dynamic and unknown environment. Thus, the characterization of the water quality state of a water mass becomes a challenge. This paper proposes a variational autoencoder structure, t[...]
Our summary: Prediction of oil contamination evolution using variational autoencoder trained in a model-free manner. Testing in different environments with accurate future contamination distribution predictions. Robustness against unseen scenarios and monitoring information effects evaluated.
Variational Autoencoder, Oil Contamination, Water Monitoring, Autonomous Surface Vehicles
Publication
Noise-Aware UAV Path Planning in Urban Environment with Reinforcement Learning
Published on 2025-03-07 by Shahin Sarhan, Marco Rinaldi, Stefano Primatesta, Giorgio Guglieri @MDPI
Abstract: This research presents a comprehensive approach for mitigating noise pollution from Unmanned Aerial Vehicles (UAVs) in urban environment by using Reinforcement Learning (RL) for flight path planning. Focusing on the city of Turin, Italy, the study utilizes its diverse urban architecture to develop a detailed 3D occupancy grid map, and a population density map. A dynamic noise source model adjusts noise emissions based on the UAV velocity, while acoustic ray tracing simulates noise propagation in[...]
Our summary: Comprehensive approach for noise-aware UAV path planning in urban environment using reinforcement learning, focusing on Turin, Italy, with simulation results showing significant noise reduction.
Reinforcement Learning, UAV Path Planning, Noise Pollution, Urban Environment
Publication
Impact of Techniques and Scanning Strategies
Published on 2025-03-06 by Seungwon Baek, Kwonil Kim, Jung-Hoon Kim, GyuWon Lee @MDPI
Abstract: The turbulent energy dissipation rate (EDR) is a quantitative measure of turbulence intensity, and it is widely used across various fields. Accurate estimation of EDR using Doppler lidar depends on the choice of estimation technique and scanning strategy. Therefore, a comparison of the techniques is still required to achieve an accurate estimation. However, the effect of the choice on estimation accuracy remains uncertain. This study systematically evaluates the accuracy of EDR estimation techni[...]
Our summary: Impact of Techniques and Scanning Strategies on EDR estimation accuracy using Doppler lidar is evaluated through a comparison of vertically pointing and Plan Position Indicator scanning strategies. EDRVAD shows positive correlation with sonic anemometers, while EDRVP techniques exhibit high agreement.
Doppler lidar, Turbulence intensity, Scanning strategies, Estimation techniques
Publication
Unified boundary machine learning model for autonomous vehicles
Patent published on the 2025-03-06 in WO under Ref WO2025048871 by AURORA OPERATIONS INC [US] (Chaabane Mohamed [us], Kaplan Benjamin [us], Litvin Yevgeni [us], O'hara Stephen [us], Vig Sean [us])
Abstract: A unified boundary machine learning model is capable of processing perception data received from various types of perception sensors on an autonomous vehicle to generate perceived boundaries of various semantic boundary types. Such perceived boundaries may then be used, for example, to control the autonomous vehicle, e.g., by generating a trajectory therefor. In some instances, the various semantic boundary types detectable by a unified boundary machine learning model may include at least a virt[...]
Our summary: Unified boundary machine learning model processes perception data from various sensors on autonomous vehicles to generate perceived boundaries for vehicle control, including virtual construction and other types of boundaries.
machine learning, autonomous vehicles, perception sensors, semantic boundaries
Patent
Integrated sensor assembly
Patent published on the 2025-03-06 in WO under Ref WO2025049123 by PLUSAI INC [US] (Deck James Wiley [us], Bharwani Murad Mehdi Mohammad [us])
Abstract: An integrated sensor assembly is described. The integrated sensor assembly can include a housing comprising a compartment. The housing can be arranged on a side surface of a cabin of an autonomous vehicle and within a threshold distance of a cabin roof of the autonomous vehicle. The assembly can include a first sensor arranged in the compartment, the first sensor configured to receive a first signal from a vehicle computer and collect information for mapping an environment of the autonomous vehi[...]
Our summary: Integrated sensor assembly with housing and compartment for sensors and light source in autonomous vehicle. Light source emits patterns for indicating hazards, turns, or autonomous mode towards the rear of the vehicle.
sensor assembly, housing, compartment, autonomous vehicle
Patent
EN 
FR 
DE 
ES 
IT