Pub Date : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551195
Lifan Xu, Shunqiao Sun, K. Mishra
We propose an automotive radar system that transmits at non-uniform pulse repetition frequency (PRF) to achieve high-resolution range and Doppler estimation while transmitting sparsely along slow-time following the difference co-chirps schemes, e.g., coprime and nested chirps. At the receiver, the radar admits undersampled slow-time signals for Doppler estimation. In a single coherent processing interval (CPI), the missing Doppler samples along slow-time are interpolated via a Doppler covariance matrix that is constructed using fast-time samples. Our co-chirp joint range-Doppler estimation with Doppler de-aliasing (CoDDler) algorithm jointly estimates the range and Doppler. The Doppler spectrum obtained from the interpolated Doppler samples are utilized to de-aliase any false Doppler peaks in the sparse estimation. The proposed non-uniform PRF automotive radar provides the possibility for transmission coordination in a time division multiplexing fashion to avoid mutual interference by saving nearly 88% of time-on-target.
{"title":"Difference Co-Chirps-Based Non-Uniform PRF Automotive FMCW Radar","authors":"Lifan Xu, Shunqiao Sun, K. Mishra","doi":"10.1109/ICAS49788.2021.9551195","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551195","url":null,"abstract":"We propose an automotive radar system that transmits at non-uniform pulse repetition frequency (PRF) to achieve high-resolution range and Doppler estimation while transmitting sparsely along slow-time following the difference co-chirps schemes, e.g., coprime and nested chirps. At the receiver, the radar admits undersampled slow-time signals for Doppler estimation. In a single coherent processing interval (CPI), the missing Doppler samples along slow-time are interpolated via a Doppler covariance matrix that is constructed using fast-time samples. Our co-chirp joint range-Doppler estimation with Doppler de-aliasing (CoDDler) algorithm jointly estimates the range and Doppler. The Doppler spectrum obtained from the interpolated Doppler samples are utilized to de-aliase any false Doppler peaks in the sparse estimation. The proposed non-uniform PRF automotive radar provides the possibility for transmission coordination in a time division multiplexing fashion to avoid mutual interference by saving nearly 88% of time-on-target.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126916219","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551133
D. Angley, S. Mehrkanoon, B. Moran, C. Gilliam, S. Simakov
Sonobuoy fields, comprising a network of sonar transmitters and receivers, are used to search for and track underwater targets. Although normally such fields are operated from a maritime patrol aircraft, automated scheduling and processing creates opportunities for employing them as autonomous sensor systems. The automated search mechanism considered in this work is controlled by modelling the presence of undetected threats in an Operational Area (OA) using a spatial probability density function (PDF), known as a threat map. The algorithm decides how to schedule waveform transmissions, known as pings, to efficiently search and clear the OA. A conventional approach is to update the threat map based on just the characteristics of the sonobuoy field and switch to a separate metric to track a target after track confirmation. In this study we address the phase when there are potential contacts which cannot yet be promoted to confirmed tracks. We develop a mechanism for probing the associated areas of interest while still remaining in the threat map driven search scheduling. To this end, we propose reinitialising the threat map after each transmission using an augmented PDF, where unconfirmed tracks are represented by weighted Gaussians. Simulations show that this approach significantly improves search performance, reducing the number of pings required to confirm a track, distance from a confirmed track to the target and the proportion of falsely confirmed tracks.
{"title":"Improving Automated Search for Underwater Threats Using Multistatic Sensor Fields by Incorporating Unconfirmed Track Information","authors":"D. Angley, S. Mehrkanoon, B. Moran, C. Gilliam, S. Simakov","doi":"10.1109/ICAS49788.2021.9551133","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551133","url":null,"abstract":"Sonobuoy fields, comprising a network of sonar transmitters and receivers, are used to search for and track underwater targets. Although normally such fields are operated from a maritime patrol aircraft, automated scheduling and processing creates opportunities for employing them as autonomous sensor systems. The automated search mechanism considered in this work is controlled by modelling the presence of undetected threats in an Operational Area (OA) using a spatial probability density function (PDF), known as a threat map. The algorithm decides how to schedule waveform transmissions, known as pings, to efficiently search and clear the OA. A conventional approach is to update the threat map based on just the characteristics of the sonobuoy field and switch to a separate metric to track a target after track confirmation. In this study we address the phase when there are potential contacts which cannot yet be promoted to confirmed tracks. We develop a mechanism for probing the associated areas of interest while still remaining in the threat map driven search scheduling. To this end, we propose reinitialising the threat map after each transmission using an augmented PDF, where unconfirmed tracks are represented by weighted Gaussians. Simulations show that this approach significantly improves search performance, reducing the number of pings required to confirm a track, distance from a confirmed track to the target and the proportion of falsely confirmed tracks.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"155 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113999884","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551150
Amir Zakerimanesh, T. Qiu, M. Tavakoli
Platooning which is defined as controlling a group of autonomous vehicles (multiple followers and one leader) to have a desired distance between them while following a desired trajectory has caught on recently in the control engineering discipline. Platooning brings along promising advantages, namely, increasing highway capacity and safety, and reducing fuel consumption. In this paper, using linearized longitudinal dynamic models for each vehicle, we investigate the control problem of vehicular platooning to have all vehicles followed the leader under a constant spacing policy. Under decentralized linear feedback controllers and taking account of heterogeneity in the dynamic models and feedback information to the vehicles, a general dynamic representation for the platoon is obtained. Having this and the proposed controller, stability analysis is developed for any information flow topology (IFT) between vehicles and any number of vehicles. As a case study, a platoon with one leader and two followers is investigated through the proposed strategy, and its stability conditions are provided. Numerical simulations are provided in which the stability range of control gains and the effect of different FTs on the performance of the platoon are discussed.
{"title":"Heterogeneous Vehicular Platooning with Stable Decentralized Linear Feedback Control","authors":"Amir Zakerimanesh, T. Qiu, M. Tavakoli","doi":"10.1109/ICAS49788.2021.9551150","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551150","url":null,"abstract":"Platooning which is defined as controlling a group of autonomous vehicles (multiple followers and one leader) to have a desired distance between them while following a desired trajectory has caught on recently in the control engineering discipline. Platooning brings along promising advantages, namely, increasing highway capacity and safety, and reducing fuel consumption. In this paper, using linearized longitudinal dynamic models for each vehicle, we investigate the control problem of vehicular platooning to have all vehicles followed the leader under a constant spacing policy. Under decentralized linear feedback controllers and taking account of heterogeneity in the dynamic models and feedback information to the vehicles, a general dynamic representation for the platoon is obtained. Having this and the proposed controller, stability analysis is developed for any information flow topology (IFT) between vehicles and any number of vehicles. As a case study, a platoon with one leader and two followers is investigated through the proposed strategy, and its stability conditions are provided. Numerical simulations are provided in which the stability range of control gains and the effect of different FTs on the performance of the platoon are discussed.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117148714","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551180
E. Chatzikalymnios, K. Moustakas
Unmanned Aerial Vehicles (UAVs) technology has enabled the design of many diverse applications in recent years. The development of autonomous landing methods has become a core task, as UAV’s navigate in remote and usually unknown environments. In this study we present a vision-based autonomous landing system for UAVs equipped with a stereo camera and an inertial measurement unit (IMU). We utilize stereo processing to acquire the 3D reconstruction of the scene. Next, we evaluate and quantity into map-metrics the factors of the terrain that are crucial for a safe landing. The optimal landing site in terms of flatness, steepness and inclination across the scene is chosen. The pose estimation is obtained by the fusion of stereo ORB-SLAM2 measurements with data from the inertial sensors, assuming no GPS signal. We evaluate the utility of our system using a multifaceted dataset and trials in real-world environments.
{"title":"Autonomous vision-based landing of UAV’s on unstructured terrains","authors":"E. Chatzikalymnios, K. Moustakas","doi":"10.1109/ICAS49788.2021.9551180","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551180","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) technology has enabled the design of many diverse applications in recent years. The development of autonomous landing methods has become a core task, as UAV’s navigate in remote and usually unknown environments. In this study we present a vision-based autonomous landing system for UAVs equipped with a stereo camera and an inertial measurement unit (IMU). We utilize stereo processing to acquire the 3D reconstruction of the scene. Next, we evaluate and quantity into map-metrics the factors of the terrain that are crucial for a safe landing. The optimal landing site in terms of flatness, steepness and inclination across the scene is chosen. The pose estimation is obtained by the fusion of stereo ORB-SLAM2 measurements with data from the inertial sensors, assuming no GPS signal. We evaluate the utility of our system using a multifaceted dataset and trials in real-world environments.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115532172","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551199
Ashkan Samadi, Marwan Ammar, O. Mohamed
In order to assess the reliability of autonomous systems, fault tree analysis (FTA) technique is used extensively. Most of the traditional FTA approaches are based on simulation and often require extensive computing capabilities. This paper proposes a formal FTA approach that can investigate the probability of failure of autonomous systems. The proposed methodology takes advantage of both FTA and statistical model checking (SMC). In order to illustrate the proposed approach, the sources of communication failure in a fleet of UAVs are analyzed. After detecting the most critical causes of communication failure, several redundant architectures are examined to assess their potentials to mitigate the risks of system failure. The results illustrate that all of the investigated architectures are capable of mitigating the probability of failure of the fleet of UAVs under studies.
{"title":"Fault Tree Analysis And Risk Mitigation Strategies For Autonomous Systems Via Statistical Model Checking","authors":"Ashkan Samadi, Marwan Ammar, O. Mohamed","doi":"10.1109/ICAS49788.2021.9551199","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551199","url":null,"abstract":"In order to assess the reliability of autonomous systems, fault tree analysis (FTA) technique is used extensively. Most of the traditional FTA approaches are based on simulation and often require extensive computing capabilities. This paper proposes a formal FTA approach that can investigate the probability of failure of autonomous systems. The proposed methodology takes advantage of both FTA and statistical model checking (SMC). In order to illustrate the proposed approach, the sources of communication failure in a fleet of UAVs are analyzed. After detecting the most critical causes of communication failure, several redundant architectures are examined to assess their potentials to mitigate the risks of system failure. The results illustrate that all of the investigated architectures are capable of mitigating the probability of failure of the fleet of UAVs under studies.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124941564","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551174
Soheyl Khalilpourazari, Hossein Hashemi Doulabi
In December 2020, a new strain of coronavirus was found in Wuhan, China. The virus causes COVID-19, a severe respiratory illness. Up to date, the virus has spread rapidly to many countries, and more than 103 million cases and 2 million death has been reported worldwide. France is one of the European Union countries that has reported more than 3 million cases and 76 thousand death. Prediction of the COVID-19 pandemic growth is essential to enable governments to put new measures to slow down the spread of the virus. Due to the virus’s novelty, providing an efficient method to predict pandemic growth is a challenging task. This research applies a recent reinforcement learning-based algorithm to a recently developed model to simulate the COVID-19 pandemic in France. We provide essential information about the pandemic growth in the country in every period in which the government of France has taken action to limit the pandemic or relaxed existing restrictions. We derive the values of the pandemic parameters, including reproduction rate, which gives us essential information about the pandemic. This information will help policymakers and healthcare professionals to plan for future measures limiting community transmission. Besides, we performed sensitivity analyses to determine the most critical parameters that accelerate the pandemic.
{"title":"Using reinforcement learning to forecast the spread of COVID-19 in France","authors":"Soheyl Khalilpourazari, Hossein Hashemi Doulabi","doi":"10.1109/ICAS49788.2021.9551174","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551174","url":null,"abstract":"In December 2020, a new strain of coronavirus was found in Wuhan, China. The virus causes COVID-19, a severe respiratory illness. Up to date, the virus has spread rapidly to many countries, and more than 103 million cases and 2 million death has been reported worldwide. France is one of the European Union countries that has reported more than 3 million cases and 76 thousand death. Prediction of the COVID-19 pandemic growth is essential to enable governments to put new measures to slow down the spread of the virus. Due to the virus’s novelty, providing an efficient method to predict pandemic growth is a challenging task. This research applies a recent reinforcement learning-based algorithm to a recently developed model to simulate the COVID-19 pandemic in France. We provide essential information about the pandemic growth in the country in every period in which the government of France has taken action to limit the pandemic or relaxed existing restrictions. We derive the values of the pandemic parameters, including reproduction rate, which gives us essential information about the pandemic. This information will help policymakers and healthcare professionals to plan for future measures limiting community transmission. Besides, we performed sensitivity analyses to determine the most critical parameters that accelerate the pandemic.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121072894","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551109
Pengshan Chen, W. Wang, Jingjie Gao
Interference suppression using adaptive nulling algorithm is an important array signal processing technique for radar/sonar sensing. However, in long term task, most of the arrays’ parameters vary from time to time, which need known sources to re-calibrate. To be free of calibration sources, this paper presents an adaptive nulling algorithm using array observation data. We first establish the model of steering vector (SV) mismatches due to gain-phase error and sensor shifting. Then the angle-related bases of received signal subspace are estimated by applying a joint optimization method consists of Genetic algorithm (GA) and quasi-Newton method. In the end, the array weighting vector can be calculated, and the results of several numerical simulations are demonstrated, which shows that the proposed algorithm can significantly improve the interference suppression performance of sensor array.
{"title":"Interference Suppression Using Adaptive Nulling Algorithm Without Calibration Sources","authors":"Pengshan Chen, W. Wang, Jingjie Gao","doi":"10.1109/ICAS49788.2021.9551109","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551109","url":null,"abstract":"Interference suppression using adaptive nulling algorithm is an important array signal processing technique for radar/sonar sensing. However, in long term task, most of the arrays’ parameters vary from time to time, which need known sources to re-calibrate. To be free of calibration sources, this paper presents an adaptive nulling algorithm using array observation data. We first establish the model of steering vector (SV) mismatches due to gain-phase error and sensor shifting. Then the angle-related bases of received signal subspace are estimated by applying a joint optimization method consists of Genetic algorithm (GA) and quasi-Newton method. In the end, the array weighting vector can be calculated, and the results of several numerical simulations are demonstrated, which shows that the proposed algorithm can significantly improve the interference suppression performance of sensor array.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130588829","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551147
Gabriela Gresenz, Jules White, D. Schmidt
This paper describes the structure and functionality of a dataset designed to enable autonomous vehicles to learn about off-road terrain using a single monocular image. This dataset includes over 12,000 images of off-road terrain and the corresponding sensor data from a global positioning system (GPS), inertial measurement units (IMUs), and a wheel rotation speed sensor. The paper also describes and empirically evaluates eight roughness labeling schemas derived from IMU z-axis acceleration for labeling the images in our dataset. These roughness labels can be used for training deep learning models to detect terrain roughness.
{"title":"An Off-Road Terrain Dataset Including Images Labeled With Measures Of Terrain Roughness","authors":"Gabriela Gresenz, Jules White, D. Schmidt","doi":"10.1109/ICAS49788.2021.9551147","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551147","url":null,"abstract":"This paper describes the structure and functionality of a dataset designed to enable autonomous vehicles to learn about off-road terrain using a single monocular image. This dataset includes over 12,000 images of off-road terrain and the corresponding sensor data from a global positioning system (GPS), inertial measurement units (IMUs), and a wheel rotation speed sensor. The paper also describes and empirically evaluates eight roughness labeling schemas derived from IMU z-axis acceleration for labeling the images in our dataset. These roughness labels can be used for training deep learning models to detect terrain roughness.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"33 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124410079","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551111
Giulia Slavic, P. Marín, David Martín, L. Marcenaro, C. Regazzoni
When performing anomaly detection on an autonomous vehicle’s sensory data, it is fundamental to infer the cause of the found anomalies. This paper proposes a method for learning prediction models and detecting anomalies by decomposing the evolution of an agent’s state into its different motion-related parameters. A filter is introduced based on Generalized Filtering to increase the interpretability of the results with respect to previous methods. The proposed anomaly detection method is tested on data from a real vehicle. We also consider the case in which multiple models are learned, how to extract the salient discriminatory features of each, and use the proposed anomaly detection method to perform behavior classification.
{"title":"Interpretable Anomaly Detection Using A Generalized Markov Jump Particle Filter","authors":"Giulia Slavic, P. Marín, David Martín, L. Marcenaro, C. Regazzoni","doi":"10.1109/ICAS49788.2021.9551111","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551111","url":null,"abstract":"When performing anomaly detection on an autonomous vehicle’s sensory data, it is fundamental to infer the cause of the found anomalies. This paper proposes a method for learning prediction models and detecting anomalies by decomposing the evolution of an agent’s state into its different motion-related parameters. A filter is introduced based on Generalized Filtering to increase the interpretability of the results with respect to previous methods. The proposed anomaly detection method is tested on data from a real vehicle. We also consider the case in which multiple models are learned, how to extract the salient discriminatory features of each, and use the proposed anomaly detection method to perform behavior classification.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127594964","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 : 2021-08-11DOI: 10.1109/ICAS49788.2021.9551160
Xiaoming Li, Jie Gao, Chun Wang, Xiao Huang, Yimin Nie
In this paper, we study a one-to-one matching ride-sharing problem to save the travellers’ total travel time considering travel time uncertainty. Unlike the existing work where the uncertainty set is assumed to be known or roughly estimated, in this work, we propose a learning-based robust optimization framework to handle the issue properly. Specifically, we assume the travel time varies in an uncertainty set which is predicted by a machine learning approach- ARIMA using travel time historical data, the predicted uncertainty set then serves as the input parameter for the robust optimization model. To evaluate the proposed approach, we conduct a group of numerical experiments based on New York taxi trip record data sets. The results show that our proposed data-driven robust optimization approach outperforms the robust optimization model with a given uncertainty set in terms of total travel time savings. Further, the proposed approach can improve the travel time savings up to 112.8%, and 34% by average. Most importantly, our proposed approach is capable of handling the uncertainty in a more effective way when the uncertainty degrees become high.
{"title":"Order Dispatching in Ride-Sharing Platform under Travel Time Uncertainty: A Data-Driven Robust Optimization Approach","authors":"Xiaoming Li, Jie Gao, Chun Wang, Xiao Huang, Yimin Nie","doi":"10.1109/ICAS49788.2021.9551160","DOIUrl":"https://doi.org/10.1109/ICAS49788.2021.9551160","url":null,"abstract":"In this paper, we study a one-to-one matching ride-sharing problem to save the travellers’ total travel time considering travel time uncertainty. Unlike the existing work where the uncertainty set is assumed to be known or roughly estimated, in this work, we propose a learning-based robust optimization framework to handle the issue properly. Specifically, we assume the travel time varies in an uncertainty set which is predicted by a machine learning approach- ARIMA using travel time historical data, the predicted uncertainty set then serves as the input parameter for the robust optimization model. To evaluate the proposed approach, we conduct a group of numerical experiments based on New York taxi trip record data sets. The results show that our proposed data-driven robust optimization approach outperforms the robust optimization model with a given uncertainty set in terms of total travel time savings. Further, the proposed approach can improve the travel time savings up to 112.8%, and 34% by average. Most importantly, our proposed approach is capable of handling the uncertainty in a more effective way when the uncertainty degrees become high.","PeriodicalId":287105,"journal":{"name":"2021 IEEE International Conference on Autonomous Systems (ICAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130690226","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：