Product Design, Manufacturing & Innovation Resources

Latest Publications & Patents on Autonomous Vehicles

Autonomous Vehicles

Tip: further to the selection below, you can search and filter our 2 entire databases:

> free publications search tool < par auteur, sujet, mots-clés, date ou revue.

> free patents search tool < pour les brevets en anglais de l'Office européen des brevets.

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.

System and method for offline 3d object detection in traffic scenes using lidar data with multiple resolutions

Patent published on the 2026-10-15 in US under Ref US20260316782 by TORC ROBOTICS INC [US] (Li Dalong [us], Shoaib Syed Taha [us], Zhu Xinxiang [us], Badgett Marcus [us], Fei Juncong [de])

Abstract: A system of an autonomous vehicle is described. The autonomous vehicle is configured to collect point cloud data associated with a current time, perform a dynamic object detection on the point cloud data to identify at least one dynamic object, and apply a dynamic object weight to the at least one dynamic object. The autonomous vehicle is further configured to retrieve point cloud data associated with at least one additional period of time, aggregate the point cloud data associated with the curr[...]


Our summary: The system detects dynamic and static objects in traffic scenes using lidar data. It aggregates point cloud data from multiple time periods for comprehensive analysis. The vehicle applies weights to identified objects to enhance detection accuracy.

Lidar, 3D object detection, autonomous vehicle, point cloud data

Patent

An oceanographic lidar system

Patent published on the 2026-10-15 in WO under Ref WO2026213658 by MACQUARIE UNIV [AU] (Kitzler Ondrej [au], Downes James [au], Pask Helen [au], Spence David [au], Artlett Christopher [au])

Abstract: Disclosed herein is a LiDAR system for probing an aquatic environment. The system comprises an excitation module, a controller module, a detector module, and a processor module. The excitation module comprises a plurality of diode lasers that are each configured to emit pulses of light towards the aquatic environment. The controller module is configured to selectively control certain parameters of the at least one of the diode lasers. The detector module is configured to receive light returned f[...]


Our summary: The disclosed LiDAR system probes aquatic environments using diode lasers to emit light pulses. It includes modules for excitation, control, detection, and processing. The system measures distance and extracts environmental information from returned light based on time-of-flight measurements.

LiDAR, aquatic environment, diode lasers, time-of-flight

Patent

Traversal risk graph-based robot path planning

Patent published on the 2026-10-15 in US under Ref US20260319514 by KOREA ADVANCED INST OF SCIENCE AND TECHNOLOGY [KR] (Myung Hyun [kr], Lee Dongkyu [kr], Yu Byeongho [kr], Oh Minho [kr], Nahrendra I Made Aswin [kr], Park Jiwon [kr], Kim Taeyun [kr])

Abstract: Disclosed is a method of traversal risk graph-based robot path planning, the method including generating a plurality of paths by connecting a plurality of nodes of the terrain on which a robot is capable of standing and two nodes among the plurality of nodes as an edge, and generating a traversal risk graph (TRG) by considering reachability of the robot to a target node and terrain characteristics; and searching for a path used for the robot to reach the target node based on the traversal risk g[...]


Our summary: The method involves generating multiple paths by connecting nodes on the terrain. A traversal risk graph is created considering the robot s reachability and terrain features. The robot then searches for a path to the target node using this graph.

robot path planning, traversal risk graph, terrain characteristics, reachability

Patent

Method and apparatus for controlling movement of robot using elevator

Patent published on the 2026-10-15 in US under Ref US20260319500 by SUNGSHIN WOMEN’S UNIV R&DB FOUNDATION [KR] (Kim Won Hee [kr], You Jaehoon [kr], Shim Soomin [kr], Hwang Seong Wook [kr], Kim Joon Young [kr], Kim Namgyo [kr], Kim Young Eun [kr], Kim Bo Kyung [kr], Ryoo Gyeongbin [kr], Oh Jeong Min [kr], Kang Ji Soo [kr])

Abstract: [0000] A method for controlling movement of a robot at an elevator includes: obtaining first sensing data of an internal space of the elevator using a camera sensor of the elevator and a weight sensor of the elevator; determining whether the robot is permitted to board the elevator based on the first sensing data; obtaining second sensing data of the internal space of the elevator using a lidar sensor disposed at the robot; based on the robot boarding the elevator, determining a first boardable [...]


Our summary: The method involves using sensors to gather data about the elevator s internal space. It assesses whether the robot can board based on this data. The robot s movement is controlled according to calculated boarding position coordinates.

robot movement, elevator control, sensing data, weight distribution

Patent

A method, apparatus, and computer-readable medium for enhancing entity perception of a machine learning model based on concept trajectories

Patent published on the 2026-10-14 in GB under Ref GB2705493 by AUMOVIO GERMANY GMBH [DE] (Georgii Mikriukov [de])

Abstract: Enhancing entity perception of a machine learning model using a sequence of data units; extracting, from a layer of the model, a local concept vector for each data unit. Entities in each local concept vector are identified by obtaining a concept trajectory of each entity by connecting the local concept vectors of the entity across consecutive data units of the sequence of data units. Analysis of the concept trajectories allows identification of perception anomalies of the one or more entities ba[...]


Our summary: A method enhances entity perception in machine learning models using concept trajectories. It extracts local concept vectors from data units to identify perception anomalies. The model adjusts based on the analysis of these anomalies to improve performance in applications like computer vision and autonomous driving.

entity perception, machine learning, concept trajectories, perception anomalies

Patent

Point cloud-based guardrail recognition device and method

Patent published on the 2026-10-14 in EP under Ref EP4822400 by BITSENSING INC [KR] (Song Heemang [kr])

Abstract: [0001] The present disclosure relates to a point cloud-based guardrail recognition device and method using Hough transform, and includes filtering, from point cloud data collected through a LiDAR sensor or a radar sensor, only point cloud data related to stationary objects, performing a Hough transform on point cloud data related to each stationary object and selecting a valid guardrail candidate group exceeding a threshold from each Hough transform result, distinguishing between a straight line[...]


Our summary: The method uses point cloud data from LiDAR or radar sensors to filter stationary objects. It applies Hough transform to identify valid guardrail candidates and distinguishes between straight lines and curves. Finally, it calculates line information to recognize the position and direction of the guardrail.

point cloud, guardrail recognition, Hough transform, LiDAR sensor

Patent

An improved Escape algorithm with multi-strategy enhancement for solving global optimum problems

Published on 2026-08-27 by @OXFORD

Abstract: AbstractThe Escape algorithm (ESC), which simulates crowd evacuation behavior, is a novel algorithm. However, it has certain limitations in terms of convergence speed and the avoidance of local optima. This paper proposes a multi-strategy enhanced variant (ESCSA), which introduces three key improvements: First, it incorporates a dynamic mask probability adjustment mechanism that adapts the dimension update ratio throughout the iteration process, thereby achieving a better balance between explora[...]


Our summary: The paper presents an enhanced Escape algorithm (ESCSA) that improves convergence speed and avoids local optima through a dynamic mask probability adjustment, stagnation detection with Simulated Annealing, and a worst-elimination strategy. ESCSA outperformed 11 algorithms in the CEC 2017 benchmark suite, achieving the best overall performance across multiple dimensions. Additionally, it demonstrated strong results in engineering design problems and effectively planned paths for mobile robots in static environments.

Escape algorithm, multi-strategy enhancement, optimization, local optima

Publication

Comprehensive performance evaluation and three-dimensional UAV trajectory path planning under multiple constraints

Published on 2026-06-25 by @OXFORD

Abstract: AbstractThe Kepler Optimization Algorithm (KOA), as a recently developed metaheuristic algorithm, has demonstrated promising performance in various optimization tasks. However, its performance is still constrained by slow convergence speed, limited convergence accuracy, and an imbalance between exploration and exploitation capabilities. To overcome these limitations, this paper proposes a multi-strategy improved Kepler Optimization Algorithm, termed the Sophisticated Policies-based Kepler Optimi[...]


Our summary: The paper introduces the Sophisticated Policies-based Kepler Optimization Algorithm (SPKOA) to enhance the original Kepler Optimization Algorithm. SPKOA employs techniques such as Latin Hypercube Sampling and a dynamic Lévy flight mechanism to improve exploration and exploitation balance. Experimental results indicate that SPKOA outperforms existing algorithms in both optimization accuracy and three-dimensional UAV path planning under complex constraints.

Kepler Optimization Algorithm, UAV trajectory planning, multi-strategy improvement, optimization performance

Publication

Sujets abordés : Autonomous Vehicles, Self-Driving, LIDAR, Road Mapping, Fleet Management, Navigation Algorithm, Path Planning, Reinforcement Learning, Lane Detection, Dual Camera, Machine Learning, Perception Sensors, Semantic Boundaries, Integrated Sensor Assembly, Map Data, Discrepancies, Noise Pollution, Urban Environment, ISO 26262, ISO/PAS 21448, ISO 15118, ISO 26262-6, and ISO 21434..

Contexte historique

2000
2002
2010
2013
2000
2000
2003
2010
2013-09-24

(si la date est inconnue ou non pertinente, par exemple « mécanique des fluides », une estimation arrondie de son émergence notable est fournie)

10e année anniversaire

Les images en pleine résolution et les téléchargements sont uniquement disponibles, et 100% gratuits, pour les membres inscrits.