EU Long-term Dataset with Multiple Sensors for Autonomous Driving

Yan, Zhi; Sun, Li; Krajník, Tomáš; Ruichek, Yassine

doi:10.1109/iros45743.2020.9341406

Cited by 58 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It usually only requires a few [13], [14] or even no [15] manually annotated samples to learn a high-performance model. Apart from this, the benefits it brings also include alleviating the computational burden when updating the model and improving the timeliness of the model, which is fully consistent with the development needs of autonomous driving for in-situ deployment [12] and long-term autonomy [9], [10], [16].…”

Section: Introductionmentioning

confidence: 77%

“…On the other hand, perception systems based on multimodal sensors are still the preferred solution for self-driving car developers, as there is no almighty and perfect sensor so far, and they all have limitations and edge cases [9]. In the past ten years, extensive research has been conducted on the use of multiple sensors for 3D object detection and tracking in the field of autonomous driving, and it is expected that more competitive performance can be obtained by effectively integrating the advantages of different sensors [5], [23].…”

Section: Related Workmentioning

confidence: 99%

“…More challenging, in response to the changing environment [9], [10] and environment changes [11], [12], a featurebased model usually needs to be fine-tuned or even retrained to achieve acceptable performance over time or in new…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving

Yang¹,

Yan²,

Tao³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Autonomous driving has achieved rapid development over the last few decades, including the machine perception as an important issue of it. Although object detection based on conventional cameras has achieved remarkable results in 2D/3D, non-visual sensors such as 3D LiDAR still have incomparable advantages in the accuracy of object position detection. However, the challenge also exists with the difficulty in properly interpreting point cloud generated by LiDAR. This paper presents a multi-modal-based online learning system for 3D LiDAR-based object classification in urban environments, including cars, cyclists and pedestrians. The proposed system aims to effectively transfer the mature detection capabilities based on visual sensors to the new model learning based on non-visual sensors through a multi-target tracker (i.e. using one sensor to train another). In particular, it integrates the Online Random Forests (ORF) [1] method, which inherently has the abilities of fast and multi-class learning. Through experiments, we show that our system is capable of learning a high-performance model for LiDAR-based 3D object classification on-the-fly, which is especially suitable for robotics in-situ deployment while responding to the widespread challenge of insufficient detector generalization capabilities.

show abstract

Section: Introductionmentioning

confidence: 77%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving

Yang¹,

Yan²,

Tao³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to validate the MHE localization scheme, several numerical and experimental data sets are used: (1) a simulated data of 3D motion of an aerial vehicle; (2) several scenarios from EU long-term dataset for autonomous driving (Yan et al, 2019); and (3) experimental sequences generated using Summit-XL Steel omni-directional mobile robot, see Figure 4. All the experiments and dataset runs are performed using a computer with Intel i7-8850H 6-core processor running at 2.60 GHz and a 16 GB RAM.…”

Section: Data Sets Used For Simulations and Experimentsmentioning

confidence: 99%

“…The data was collected using the University of Technology of Belfort Montbliard (UTBM) vehicle in human driving mode. The vehicle is driven in the downtown of Montpelier in France (Yan et al, 2019). For the long-term data, the driving distance is about 5.0 km per session driven in 16 minutes.…”

Section: Eu Long-term Datasetmentioning

confidence: 99%

A generic multi-sensor fusion scheme for localization of autonomous platforms using moving horizon estimation

Osman

Mehrez

Daoud

et al. 2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

In this paper, a generic multi-sensor fusion framework is developed for the localization of intelligent vehicles and mobile robots. The localization framework is based on moving horizon estimation (MHE). Unlike the commonly used probabilistic filtering algorithms – for example, extended Kalman filter (EKF) and unscented Kalman filter (UKF) – MHE relies on solving successive least squares optimization problems over the innovation of multiple sensors’ measurements and a specific estimation horizon. In this paper, we present an efficient and generic multi-sensor fusion scheme, based on MHE. The proposed multi-sensor fusion scheme is capable of operating with different sensors’ rates, missing measurements, and outliers. Moreover, the proposed scheme is based on a multi-threading architecture to reduce its computational cost, making it more feasible for practical applications. The MHE fusion method is tested using simulated data as well as real experimental data sequences from an intelligent vehicle and a mobile robot combining measurements from different sensors to get accurate localization results. The performance of MHE is compared against that of UKF, where the MHE estimation results show superior performance.

show abstract

Point‐LIO: Robust High‐Bandwidth Light Detection and Ranging Inertial Odometry

Wei

Chen

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Herein, point light detection and ranging inertial odometry (LIO) is presented: a robust and high‐bandwidth light detection and ranging (LiDAR) inertial odometry with the capability to estimate extremely aggressive robotic motions. Point‐LIO has two key novelties. The first one is a point‐by‐point LIO framework that updates the state at each LiDAR point measurement. This framework allows an extremely high‐frequency odometry output, significantly increases the odometry bandwidth, and fundamentally removes the artificial in‐frame motion distortion. The second one is a stochastic process‐augmented kinematic model which models the IMU measurement as an output. This new modeling method enables accurate localization and reliable mapping for aggressive motions even with inertial measurement unit (IMU) measurements saturated in the middle of the motion. Various real‐world experiments are conducted for performance evaluation. Overall, Point‐LIO is capable to provide accurate, high‐frequency odometry (4–8 kHz) and reliable mapping under severe vibrations and aggressive motions with high angular velocity (75 rad s−1) beyond the IMU measuring ranges. Furthermore, an exhaustive benchmark comparison is conducted. Point‐LIO achieves consistently comparable accuracy and time consumption. Finally, two example applications of Point‐LIO are demonstrated, one is a racing drone and the other is a self‐rotating unmanned aerial vehicle, both have aggressive motions.

show abstract

EU Long-term Dataset with Multiple Sensors for Autonomous Driving

Cited by 58 publications

References 22 publications

Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving

Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving

A generic multi-sensor fusion scheme for localization of autonomous platforms using moving horizon estimation

Point‐LIO: Robust High‐Bandwidth Light Detection and Ranging Inertial Odometry

Contact Info

Product

Resources

About