Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 8(6), С. 3692 - 3711

Опубликована: Май 11, 2023

Intelligent vehicles (IVs) have gained worldwide attention due to their increased convenience, safety advantages, and potential commercial value. Despite predictions of deployment by 2025, implementation remains limited small-scale validation, with precise tracking controllers motion planners being essential prerequisites for IVs. This article reviews state-of-the-art planning methods IVs, including pipeline end-to-end methods. The study examines the selection, expansion, optimization operations in a method, while it investigates training approaches validation scenarios driving tasks Experimental platforms are reviewed assist readers choosing suitable strategies. A side-by-side comparison is provided highlight strengths limitations, aiding system-level design choices. Current challenges future perspectives also discussed this survey.

Язык: Английский

---

Chat With ChatGPT on Intelligent Vehicles: An IEEE TIV Perspective

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 8(3), С. 2020 - 2026

Опубликована: Март 1, 2023

This letter reports on a TIV DHW (decentralized and hybrid workshop) that explores the prospective influence of ChatGPT research development in intelligent vehicles. To assess update capabilities ChatGPT, we conducted tests involving both basic technically relevant questions. Our preliminary testing revealed ChatGPT's information can be updated corrected at one time, but it may take some time for changes to reflected responses, so not always possess latest knowledge regarding specific topics. We further discuss field vehicles, particularly possible applications areas like autonomous driving, human-vehicle interaction, transportation systems, highlighting challenges opportunities associated with these applications. Additionally, address technical questions, such as feasibility training vehicles using same methods reflection intelligence context human-machine shared control. In conclusion, this presents exploration potential vehicle research, from an IEEE perspective, acknowledging limitations uncertainties emerging technology.

Язык: Английский

---

HYDRO-3D: Hybrid Object Detection and Tracking for Cooperative Perception Using 3D LiDAR

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 8(8), С. 4069 - 4080

Опубликована: Июнь 12, 2023

3D-LiDAR-based cooperative perception has been generating significant interest for its ability to tackle challenges such as occlusion, sparse point clouds, and out-of-range issues that can be problematic single-vehicle perception. Despite effectiveness in overcoming various challenges, per-ception's performance still affected by the aforementioned when Connected Automated Vehicles (CAVs) operate at edges of their sensing range. Our proposed approach called HYDRO-3D aims improve object detection explicitly incorporating historical tracking information. Specifically, combines features from a state-of-the-art algorithm (V2X-ViT) with information infer objects. Afterward, novel spatial-temporal 3D neural network performing global local manipulations object-tracking data is applied generate feature map enhance detection. The method comprehensively evaluated on V2XSet. qualitative quantitative experiment results demonstrate effectively utilize achieve robust performance. It outperforms SOTA V2X-ViT 3.7% [email protected] CAVs also generalized 4.5% improvement [email protected].

Язык: Английский

---

Transportation 5.0: The DAO to Safe, Secure, and Sustainable Intelligent Transportation Systems

IEEE Transactions on Intelligent Transportation Systems, Год журнала: 2023, Номер 24(10), С. 10262 - 10278

Опубликована: Сен. 11, 2023

In 2014, IEEE Intelligent Transportation Systems Society established a Technical Committee on 5.0 with the mission of promoting and transforming deployment advanced innovative technologies, especially Artificial Intelligence in transportation. This paper briefly summarizes our main research findings over last decade. Foundation Models, Scenarios Engineering, Operating have been identified as directions for development next-generation intelligent transportation systems.

Язык: Английский

---

V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Год журнала: 2023, Номер unknown

Опубликована: Июнь 1, 2023

Modern perception systems of autonomous vehicles are known to be sensitive occlusions and lack the capability long perceiving range. It has been one key bottlenecks that prevents Level 5 autonomy. Recent research demonstrated Vehicle-to-Vehicle (V2V) cooperative system great potential revolutionize driving industry. However, a real-world dataset hinders progress this field. To facilitate development perception, we present V2V4Real, first large-scale multi-modal for V2V perception. The data is collected by two equipped with sensors together through diverse scenarios. Our V2V4Real covers area 410 km, comprising 20K LiDAR frames, 40K RGB 240K annotated 3D bounding boxes classes, HDMaps cover all routes. introduces three tasks, including object detection, tracking, Sim2Real domain adaptation We provide comprehensive benchmarks recent algorithms on tasks. can found at research.seas.ucla.edu/mobility-lab/v2v4real/.

Язык: Английский

---

Learning for Vehicle-to-Vehicle Cooperative Perception Under Lossy Communication

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 8(4), С. 2650 - 2660

Опубликована: Март 21, 2023

Deep learning has been widely used in intelligent vehicle driving perception systems, such as 3D object detection. One promising technique is Cooperative Perception, which leverages Vehicle-to-Vehicle (V2V) communication to share deep learning-based features among vehicles. However, most cooperative algorithms assume ideal and do not consider the impact of Lossy Communication (LC), very common real world, on feature sharing. In this paper, we explore effects LC Perception propose a novel approach mitigate these effects. Our includes an LC-aware Repair Network (LCRN) V2V Attention Module (V2VAM) with intra-vehicle attention uncertainty-aware inter-vehicle attention. We demonstrate effectiveness our public OPV2V dataset (a digital-twin simulated dataset) using point cloud-based results show that improves detection performance under lossy communication. Specifically, proposed method achieves significant improvement Average Precision compared state-of-the-art algorithms, proves capability effectively negative enhance interaction between ego other

Язык: Английский

---

A Systematic Survey of Control Techniques and Applications in Connected and Automated Vehicles

IEEE Internet of Things Journal, Год журнала: 2023, Номер 10(24), С. 21892 - 21916

Опубликована: Авг. 21, 2023

Vehicle control is one of the most critical challenges in autonomous vehicles (AVs) and connected automated (CAVs), it paramount vehicle safety, passenger comfort, transportation efficiency, energy saving. This survey attempts to provide a comprehensive thorough overview current state technology, focusing on evolution from estimation trajectory tracking AVs at microscopic level collaborative CAVs macroscopic level. First, this review starts with key estimation, specifically sideslip angle, which pivotal for control, discuss representative approaches. Then, we present symbolic approaches AVs. On top that, further frameworks corresponding applications. Finally, concludes discussion future research directions challenges. aims contextualized in-depth look art CAVs, identifying areas focus pointing out potential exploration.

Язык: Английский

---

Integrated Inertial-LiDAR-Based Map Matching Localization for Varying Environments

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 8(10), С. 4307 - 4318

Опубликована: Июль 26, 2023

Localization is critical for automated vehicles as it provides essential position, velocity, and heading angle information to perform object tracking, trajectory prediction, motion planning, control. However, model/environmental uncertainties (including road friction) noises in sensor measurements have a significant effect on the accuracy of localization vehicle state estimation, specially perceptually degraded conditions. In this article, an integrated method based fusion inertial dead reckoning model 3D LiDAR-based map matching proposed experimentally verified urban environment with varying environmental Leveraging global navigation satellite system (GNSS), (INS), LiDAR point clouds, novel light cloud generation method, which only keeps necessary clouds (i.e., buildings roads regardless vegetation seasonal change), proposed. Subsequently, onboard sensors pre-built map, derived normal distribution transformation (NDT) algorithm by error-state-constrained Kalman filter limit error. On top filter, stability analysis estimator presented. Finally, performance validated real experiments under various Thorough winter summer associated results confirm advantages integrating terms reduced computational complexity.

Язык: Английский

---

Foundation Intelligence for Smart Infrastructure Services in Transportation 5.0

IEEE Transactions on Intelligent Vehicles, Год журнала: 2024, Номер 9(1), С. 39 - 47

Опубликована: Янв. 1, 2024

This perspective paper delves into the concept of foundation intelligence that shapes future smart infrastructure services as transportation sector transitions era Transportation 5.0. First, discussion focuses on a suite emerging technologies essential for intelligence. These encompass digital twinning, parallel intelligence, large vision-language models, traffic simulation and systems modeling, vehicle-to-everything (V2X) connectivity, decentralized/distributed systems. Next, introduces present landscape 5.0 applications illuminated by foundational casts vision towards including cooperative driving automation, intersection/infrastructure, management, virtual drivers, mobility planning operations, laying out prospects are poised to redefine ecosystem. Last, through comprehensive outlook, this aspires offer guiding framework intelligent evolution in data generation model calibration, twinning simulation, scenario development experimentation, feedback loop management control, continuous learning adaptation, fostering safety, efficiency, reliability, sustainability infrastructure.

Язык: Английский

---

Society-Centered and DAO-Powered Sustainability in Transportation 5.0: An Intelligent Vehicles Perspective

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 8(4), С. 2635 - 2638

Опубликована: Апрель 1, 2023

As economic and social activities continue to increase, transportation is increasingly contributing climate change, air pollution other environmental damage. The growing concerns about the sustainability of are forcing everyone in this field think solutions keep our mobility environmentally, economically socially sustainable. To provide a forum for exchange ideas experiences from industry, academia public sector, we have recently held series seminars first Distributed/Decentralized Hybrid Workshop on Sustainability Transportation Logistics (DHW-STL), part Symposia (DHS-STL), Conferences (DHC-STL). This letter provides brief report First DHW-STL discusses potentials, possibilities perspectives driven by Intelligent Vehicles (IV) technologies achieve sustainable intelligent systems logistics.

Язык: Английский

---