Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186756
Alireza Rahimpour, Navid Fallahinia, D. Upadhyay, Justin Miller
The performance of the current collision avoidance systems in Autonomous Vehicles (AV) and Advanced Driver Assistance Systems (ADAS) can be drastically affected by low light and adverse weather conditions. Collisions with large animals such as deer in low light cause significant cost and damage every year. In this paper, we propose the first AI-based method for future trajectory prediction of large animals and mitigating the risk of collision with them in low light. In order to minimize false collision warnings, in our multi-step framework, first, the large animal is accurately detected and a preliminary risk level is predicted for it and low-risk animals are discarded. In the next stage a multi-stream CONV-LSTM-based encoder-decoder framework is designed to predict the future trajectory of the potentially high-risk animals. The proposed model uses camera motion prediction as well as the local and global context of the scene to generate accurate predictions. Furthermore, this paper introduces a new dataset of FIR videos for large animal detection and risk estimation in real nighttime driving scenarios. Our experiments show promising results of the proposed framework in adverse conditions. Our code is available online1.
{"title":"Deer in the headlights: FIR-based Future Trajectory Prediction in Nighttime Autonomous Driving","authors":"Alireza Rahimpour, Navid Fallahinia, D. Upadhyay, Justin Miller","doi":"10.1109/IV55152.2023.10186756","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186756","url":null,"abstract":"The performance of the current collision avoidance systems in Autonomous Vehicles (AV) and Advanced Driver Assistance Systems (ADAS) can be drastically affected by low light and adverse weather conditions. Collisions with large animals such as deer in low light cause significant cost and damage every year. In this paper, we propose the first AI-based method for future trajectory prediction of large animals and mitigating the risk of collision with them in low light. In order to minimize false collision warnings, in our multi-step framework, first, the large animal is accurately detected and a preliminary risk level is predicted for it and low-risk animals are discarded. In the next stage a multi-stream CONV-LSTM-based encoder-decoder framework is designed to predict the future trajectory of the potentially high-risk animals. The proposed model uses camera motion prediction as well as the local and global context of the scene to generate accurate predictions. Furthermore, this paper introduces a new dataset of FIR videos for large animal detection and risk estimation in real nighttime driving scenarios. Our experiments show promising results of the proposed framework in adverse conditions. Our code is available online1.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127115826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186534
Matteo Frosi, Matteo Matteucci
Autonomous driving and 3D mapping are a few applications associated with real-time six-degrees-of-freedom pose estimation of ground vehicles, especially in outdoor (e.g., urban) environments. During the past decades, many systems have been proposed, with the majority working on data coming from only one sensor, while also struggling to keep accuracy and performance balanced. In this paper, we present D3VIL-SLAM, which extends an existing LiDAR-based SLAM system, ART-SLAM, to include inertial and visual information. The front-end comprises three branches that perform short-term data association, i.e., tracking, by exploiting laser, visual, and inertial data, respectively. All motion estimates and loop constraints derived from both LiDAR scans and images are used to build a robust g2o pose graph, which is later optimized to best satisfy all motion constraints. We compare the accuracy of our system with state-of-the-art SLAM methods, showing that D3VIL-SLAM is more accurate and produces highly detailed 3D maps while retaining real-time performance. Lastly, we perform a brief ablation study with different limitations (e.g., only images are allowed). All experimental campaigns are done by evaluating the estimated trajectory displacement using the KITTI dataset.
{"title":"D3VIL-SLAM: 3D Visual Inertial LiDAR SLAM for Outdoor Environments","authors":"Matteo Frosi, Matteo Matteucci","doi":"10.1109/IV55152.2023.10186534","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186534","url":null,"abstract":"Autonomous driving and 3D mapping are a few applications associated with real-time six-degrees-of-freedom pose estimation of ground vehicles, especially in outdoor (e.g., urban) environments. During the past decades, many systems have been proposed, with the majority working on data coming from only one sensor, while also struggling to keep accuracy and performance balanced. In this paper, we present D3VIL-SLAM, which extends an existing LiDAR-based SLAM system, ART-SLAM, to include inertial and visual information. The front-end comprises three branches that perform short-term data association, i.e., tracking, by exploiting laser, visual, and inertial data, respectively. All motion estimates and loop constraints derived from both LiDAR scans and images are used to build a robust g2o pose graph, which is later optimized to best satisfy all motion constraints. We compare the accuracy of our system with state-of-the-art SLAM methods, showing that D3VIL-SLAM is more accurate and produces highly detailed 3D maps while retaining real-time performance. Lastly, we perform a brief ablation study with different limitations (e.g., only images are allowed). All experimental campaigns are done by evaluating the estimated trajectory displacement using the KITTI dataset.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"433 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116007167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186537
Daegyu Lee, Hyunwoo Nam, Chanhoe Ryu, Sun-Young Nah, D. Shim
This paper presents a localization system robust against unreliable measurements and a resilient navigation system recovering from localization failures for Indy autonomous challenge (IAC). The IAC is a competition with full-scale autonomous race cars that drive at speeds up to 300 kph. Owing to high-speed and heavy vibration in the car, a GPS/INS system is prone to degrade causing critical localization errors, which leads to catastrophic accidents.In order to address this issue, we propose a robust localization system that probabilistically evaluates the credibility of multi-modal measurements. At a correction step of the Kalman filter, a degradation identification method with a novel hyper-parameter derived from Bayesian decision theory is introduced to choose the most credible measurement values in real-time. Since the racing condition is so harsh that even our robust localization method can fail for a short period of time, we present a resilient navigation system that enables the race car to continue to follow the race track in the event of a localization failure. Our system uses direct perception information in planning and execution until the completion of localization recovery.The proposed localization system is first validated in a simulation with real measurement data contaminated by large artificial noises. The experimental validation during an actual race is also presented. The last part of our paper shows the results from the real-world tests where our system recovers from failures and prevents accidents in real-time, which proves the resilience of the proposed navigation system.
{"title":"Resilient Navigation Based on Multimodal Measurements and Degradation Identification for High-Speed Autonomous Race Cars","authors":"Daegyu Lee, Hyunwoo Nam, Chanhoe Ryu, Sun-Young Nah, D. Shim","doi":"10.1109/IV55152.2023.10186537","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186537","url":null,"abstract":"This paper presents a localization system robust against unreliable measurements and a resilient navigation system recovering from localization failures for Indy autonomous challenge (IAC). The IAC is a competition with full-scale autonomous race cars that drive at speeds up to 300 kph. Owing to high-speed and heavy vibration in the car, a GPS/INS system is prone to degrade causing critical localization errors, which leads to catastrophic accidents.In order to address this issue, we propose a robust localization system that probabilistically evaluates the credibility of multi-modal measurements. At a correction step of the Kalman filter, a degradation identification method with a novel hyper-parameter derived from Bayesian decision theory is introduced to choose the most credible measurement values in real-time. Since the racing condition is so harsh that even our robust localization method can fail for a short period of time, we present a resilient navigation system that enables the race car to continue to follow the race track in the event of a localization failure. Our system uses direct perception information in planning and execution until the completion of localization recovery.The proposed localization system is first validated in a simulation with real measurement data contaminated by large artificial noises. The experimental validation during an actual race is also presented. The last part of our paper shows the results from the real-world tests where our system recovers from failures and prevents accidents in real-time, which proves the resilience of the proposed navigation system.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122352197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186739
Jarl L. A. Lemmens, Ariyan Bighashdel, P. Jancura, Gijs Dubbelman
Pedestrian path prediction is an emerging and crucial task in numerous applications, such as autonomous vehicles. Due to the complexity of the task, various formulations are proposed throughout the literature. However, the interconnection between these formulations remains to be seen, which makes a fair comparison challenging. This work proposes a unified pedestrian path prediction framework via Markov decision process (MDP). We demonstrate that by carefully designing the components of the MDP, various standard formulations can be perceived as specific combinations of settings in our framework. Additionally, the unified framework allows us to discover new combinations of settings that integrate the benefits of current formulations improving the prediction performance. We conduct a comparison study and evaluate several formulations in well-controlled experiments. Furthermore, we carefully assess the influence of various settings, such as policy stochasticity and sequential decision-making, on prediction performance. The goal of this work is not to propose a new state-of-the- art method but to study various formulations of the pedestrian path prediction task under a unifying framework and uncover new directions that can eventually advance the current state-of-the-art.
{"title":"Unified Pedestrian Path Prediction Framework: A Comparison Study","authors":"Jarl L. A. Lemmens, Ariyan Bighashdel, P. Jancura, Gijs Dubbelman","doi":"10.1109/IV55152.2023.10186739","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186739","url":null,"abstract":"Pedestrian path prediction is an emerging and crucial task in numerous applications, such as autonomous vehicles. Due to the complexity of the task, various formulations are proposed throughout the literature. However, the interconnection between these formulations remains to be seen, which makes a fair comparison challenging. This work proposes a unified pedestrian path prediction framework via Markov decision process (MDP). We demonstrate that by carefully designing the components of the MDP, various standard formulations can be perceived as specific combinations of settings in our framework. Additionally, the unified framework allows us to discover new combinations of settings that integrate the benefits of current formulations improving the prediction performance. We conduct a comparison study and evaluate several formulations in well-controlled experiments. Furthermore, we carefully assess the influence of various settings, such as policy stochasticity and sequential decision-making, on prediction performance. The goal of this work is not to propose a new state-of-the- art method but to study various formulations of the pedestrian path prediction task under a unifying framework and uncover new directions that can eventually advance the current state-of-the-art.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122234570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186750
Kenichi Takasaki, Yuka Sasaki, Shoichiro Watanabe, Yasutaka Nishimura, Mari Abe
In the domain of connected vehicles or advanced driver assistance systems, electroencephalogram (EEG) data is measured in vehicles and used for applications in driver safety. These analysis modules are designed to detect abnormal driver states such as drowsiness, fatigue, and dangerous driving by using EEG data in real-time on edge devices since these conditions reflect a driver’s current cognitive state. However, there are few approaches to forecasting EEG data to prevent dangerous driving in advance using recent deep learning techniques. In this paper, we propose a novel generative adversarial network (W-GAN) which aims to forecast EEGs as a multivariate multi-step times series data. It consists of dilated causal convolutional layers to maintain EEG characteristics. We also propose a new performance measure reflecting the reproducibility of frequency components which confirms the feasibility of the forecasted EEG data. We conducted an experiment to evaluate our proposed model using EEG analysis research data. In the experiment, it was shown that our model outperformed several deep learning models in reproducibility of both EEG waveform and frequency components.
{"title":"GAN-based EEG Forecasting for Attaining Driving Operations","authors":"Kenichi Takasaki, Yuka Sasaki, Shoichiro Watanabe, Yasutaka Nishimura, Mari Abe","doi":"10.1109/IV55152.2023.10186750","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186750","url":null,"abstract":"In the domain of connected vehicles or advanced driver assistance systems, electroencephalogram (EEG) data is measured in vehicles and used for applications in driver safety. These analysis modules are designed to detect abnormal driver states such as drowsiness, fatigue, and dangerous driving by using EEG data in real-time on edge devices since these conditions reflect a driver’s current cognitive state. However, there are few approaches to forecasting EEG data to prevent dangerous driving in advance using recent deep learning techniques. In this paper, we propose a novel generative adversarial network (W-GAN) which aims to forecast EEGs as a multivariate multi-step times series data. It consists of dilated causal convolutional layers to maintain EEG characteristics. We also propose a new performance measure reflecting the reproducibility of frequency components which confirms the feasibility of the forecasted EEG data. We conducted an experiment to evaluate our proposed model using EEG analysis research data. In the experiment, it was shown that our model outperformed several deep learning models in reproducibility of both EEG waveform and frequency components.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128589121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186804
Fan Yang, Xueyuan Li, Qi Liu, Chaoyang Liu, Zirui Li, Yong Liu
Learning-based algorithms are gradually emerging in the field of autonomous driving due to their powerful data processing capabilities. Researchers in the field of intelligent vehicle planning and decision-making are gradually using reinforcement learning algorithms to solve related problems. The safety research of reinforcement learning algorithms is significant and widely concerned. The main reason for the safety problem of the existing reinforcement learning algorithm is that there is still a bias in the safety judgment of the current environment, and it is impossible to make directional improvements by modifying the network and training method. In this paper, an action judgment network is designed as a standard to select the optimal action, which can assist the algorithm to judge environmental safety more deeply. Firstly, the action judgment network takes the state space and action as input, and the output is the safety state of the vehicle after the action. Secondly, this work establishes the required database to train the action judgment network through deep learning and achieves the highest accuracy of 98%. Finally, the proposed algorithm is tested in three scenarios: single-lane, intersection, and roundabout. This algorithm can judge the actions according to the reinforcement learning q value table order until the optimal and safe action is selected. The results show that the newly proposed algorithm can greatly improve the safety of the algorithm without affecting vehicle speed.
{"title":"Filling Action Selection Reinforcement Learning Algorithm for Safer Autonomous Driving in Multi-Traffic Scenes","authors":"Fan Yang, Xueyuan Li, Qi Liu, Chaoyang Liu, Zirui Li, Yong Liu","doi":"10.1109/IV55152.2023.10186804","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186804","url":null,"abstract":"Learning-based algorithms are gradually emerging in the field of autonomous driving due to their powerful data processing capabilities. Researchers in the field of intelligent vehicle planning and decision-making are gradually using reinforcement learning algorithms to solve related problems. The safety research of reinforcement learning algorithms is significant and widely concerned. The main reason for the safety problem of the existing reinforcement learning algorithm is that there is still a bias in the safety judgment of the current environment, and it is impossible to make directional improvements by modifying the network and training method. In this paper, an action judgment network is designed as a standard to select the optimal action, which can assist the algorithm to judge environmental safety more deeply. Firstly, the action judgment network takes the state space and action as input, and the output is the safety state of the vehicle after the action. Secondly, this work establishes the required database to train the action judgment network through deep learning and achieves the highest accuracy of 98%. Finally, the proposed algorithm is tested in three scenarios: single-lane, intersection, and roundabout. This algorithm can judge the actions according to the reinforcement learning q value table order until the optimal and safe action is selected. The results show that the newly proposed algorithm can greatly improve the safety of the algorithm without affecting vehicle speed.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129926955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186612
Cecilia Latotzke, Amarin Kloeker, Simon Schoening, Fabian Kemper, Mazen Slimi, L. Eckstein, T. Gemmeke
Edge nodes such as Intelligent Transportation System Stations are becoming increasingly relevant in the context of automated driving as they provide connected vehicles with additional information to support their automated driving functions. However, the power budget for these edge nodes is limited and data has to be processed in real-time to be of use to automated driving functions. In this work, we present a system for processing raw lidar data in real-time on an FPGA, resulting in a significant reduction in power consumption compared to conventional hardware. Our approach leads to a 42.4% reduction in power consumption while maintaining the quality of the results. Processing two 128-layer surround-view lidar point clouds takes 522 ms per frame and an average power consumption of 39.3 W for the CPU and 34.5W for the FPGA. Our optimizations surpass the state-of-the-art by up to 193 times.
{"title":"FPGA-based Acceleration of Lidar Point Cloud Processing and Detection on the Edge","authors":"Cecilia Latotzke, Amarin Kloeker, Simon Schoening, Fabian Kemper, Mazen Slimi, L. Eckstein, T. Gemmeke","doi":"10.1109/IV55152.2023.10186612","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186612","url":null,"abstract":"Edge nodes such as Intelligent Transportation System Stations are becoming increasingly relevant in the context of automated driving as they provide connected vehicles with additional information to support their automated driving functions. However, the power budget for these edge nodes is limited and data has to be processed in real-time to be of use to automated driving functions. In this work, we present a system for processing raw lidar data in real-time on an FPGA, resulting in a significant reduction in power consumption compared to conventional hardware. Our approach leads to a 42.4% reduction in power consumption while maintaining the quality of the results. Processing two 128-layer surround-view lidar point clouds takes 522 ms per frame and an average power consumption of 39.3 W for the CPU and 34.5W for the FPGA. Our optimizations surpass the state-of-the-art by up to 193 times.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123389623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186758
Yijun Mao, Yan Ding, Chongshan Jiao, Pengju Ren
Human-driven vehicles (HDVs) will still exist for a long time as we move towards the era of connected autonomous vehicles (CAVs). It is challenging to ensure the safety of the system and improve the efficiency of convoys in mixed traffic environments due to the stochastic behaviors and uncertain intentions of HDVs. To address these issues, this paper develops an uncertainty-aware cooperative lane-changing framework, termed UCLF, for CAVs based on partially observable Markov decision process (POMDP). We extend POMDP to multi-agent cooperative lane-changing by prioritizing CAVs according to lane-changing urgency and planning for CAVs sequentially. Two novel cooperation mechanisms, namely cooperative implicit branching and cooperative explicit pruning, are proposed to promote efficiency and ensure safety. Numerical experiments are conducted to show the smooth and efficient lane-changing maneuvers under intention uncertainty. Compared to baseline, UCLF achieves up to 28.7% decrease in total travel time on average. We also validate UCLF in a real multi-AGV (Automated Guided Vehicle) system to demonstrate the usability and reliability of our study.
{"title":"UCLF: An Uncertainty-Aware Cooperative Lane-Changing Framework for Connected Autonomous Vehicles in Mixed Traffic","authors":"Yijun Mao, Yan Ding, Chongshan Jiao, Pengju Ren","doi":"10.1109/IV55152.2023.10186758","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186758","url":null,"abstract":"Human-driven vehicles (HDVs) will still exist for a long time as we move towards the era of connected autonomous vehicles (CAVs). It is challenging to ensure the safety of the system and improve the efficiency of convoys in mixed traffic environments due to the stochastic behaviors and uncertain intentions of HDVs. To address these issues, this paper develops an uncertainty-aware cooperative lane-changing framework, termed UCLF, for CAVs based on partially observable Markov decision process (POMDP). We extend POMDP to multi-agent cooperative lane-changing by prioritizing CAVs according to lane-changing urgency and planning for CAVs sequentially. Two novel cooperation mechanisms, namely cooperative implicit branching and cooperative explicit pruning, are proposed to promote efficiency and ensure safety. Numerical experiments are conducted to show the smooth and efficient lane-changing maneuvers under intention uncertainty. Compared to baseline, UCLF achieves up to 28.7% decrease in total travel time on average. We also validate UCLF in a real multi-AGV (Automated Guided Vehicle) system to demonstrate the usability and reliability of our study.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"60 3-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120896437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-04DOI: 10.1109/IV55152.2023.10186631
David Hermann, Granit Tejeci, C. M. Martinez, Gereon Hinz, Alois Knoll
As the demand for automated vehicle testing on proving grounds grows, the need for comprehensive and reliable environment monitoring systems becomes increasingly important. In highly dynamic driving test scenarios, long-range perception is essential for detecting dangers and hazards, ensuring the safety of both the test vehicle and other people on the track. However, determining an appropriate sensor setup can be challenging due to the complexity of sensor perception limitations. Perception limitations depend on the sensor characteristics and the environment. In this work, we propose a new approach to automatically evaluate sensor performance for high dynamic driving to improve the safety and efficiency of automated testing on proving grounds. Our approach involves estimating the detection range of common sensor technologies and analyzing the performance of sensor systems under various environmental conditions. By evaluating sensor performance in advance and comparing different sensor setups on tracks with a high-speed profile, we are able to identify critical track sections with higher collision risks and safeguard tests accordingly. This study emphasizes the importance of advanced environmental monitoring and sensor analysis in ensuring the safety and efficiency of automated vehicle testing.
{"title":"Automated Sensor Performance Evaluation of Robot-Guided Vehicles for High Dynamic Tests","authors":"David Hermann, Granit Tejeci, C. M. Martinez, Gereon Hinz, Alois Knoll","doi":"10.1109/IV55152.2023.10186631","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186631","url":null,"abstract":"As the demand for automated vehicle testing on proving grounds grows, the need for comprehensive and reliable environment monitoring systems becomes increasingly important. In highly dynamic driving test scenarios, long-range perception is essential for detecting dangers and hazards, ensuring the safety of both the test vehicle and other people on the track. However, determining an appropriate sensor setup can be challenging due to the complexity of sensor perception limitations. Perception limitations depend on the sensor characteristics and the environment. In this work, we propose a new approach to automatically evaluate sensor performance for high dynamic driving to improve the safety and efficiency of automated testing on proving grounds. Our approach involves estimating the detection range of common sensor technologies and analyzing the performance of sensor systems under various environmental conditions. By evaluating sensor performance in advance and comparing different sensor setups on tracks with a high-speed profile, we are able to identify critical track sections with higher collision risks and safeguard tests accordingly. This study emphasizes the importance of advanced environmental monitoring and sensor analysis in ensuring the safety and efficiency of automated vehicle testing.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124452339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The perceptual information acquired by a single vehicle-side LiDAR in autonomous driving is limited, and this phenomenon is more prominent at intersections where vehicles are turning. Existing solutions improve vehicle perception by designing complex systems to match homogeneous point clouds acquired by the same type of sensors. In this study, we propose a heterogeneous point cloud registration for vehicle-infrastructure collaboration (HPCR-VI) that supplements the missing sensory information of the vehicle-side mechanical LiDAR with the point cloud information acquired by the infrastructure-side solid-state LiDAR. The HPCR-VI framework proposed in this paper breaks the limitation of homogeneous point cloud registration and can quickly obtain alignment results from two frames of heterogeneous point clouds, whose densities and viewing angles differ greatly, solving the heterogeneous point cloud registration problem where traditional point cloud alignment methods fail. Our proposed method is tested on the DAIR-V2X dataset, and the success rate of alignment is 40-50 points higher than that of the baseline method.
{"title":"HPCR-VI: Heterogeneous point cloud registration for vehicle-infrastructure collaboration","authors":"Yuting Zhao, Xinyu Zhang, Shiyan Zhang, Shaoting Qiu, Haojie Yin, Xu Zhang","doi":"10.1109/IV55152.2023.10186606","DOIUrl":"https://doi.org/10.1109/IV55152.2023.10186606","url":null,"abstract":"The perceptual information acquired by a single vehicle-side LiDAR in autonomous driving is limited, and this phenomenon is more prominent at intersections where vehicles are turning. Existing solutions improve vehicle perception by designing complex systems to match homogeneous point clouds acquired by the same type of sensors. In this study, we propose a heterogeneous point cloud registration for vehicle-infrastructure collaboration (HPCR-VI) that supplements the missing sensory information of the vehicle-side mechanical LiDAR with the point cloud information acquired by the infrastructure-side solid-state LiDAR. The HPCR-VI framework proposed in this paper breaks the limitation of homogeneous point cloud registration and can quickly obtain alignment results from two frames of heterogeneous point clouds, whose densities and viewing angles differ greatly, solving the heterogeneous point cloud registration problem where traditional point cloud alignment methods fail. Our proposed method is tested on the DAIR-V2X dataset, and the success rate of alignment is 40-50 points higher than that of the baseline method.","PeriodicalId":195148,"journal":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126436024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：