{"title":"DC-HEN: A Deadline-aware and Congestion-relieved Hierarchical Emergency Navigation Algorithm for Ship Indoor Environments","authors":"Xiaoli Zeng, Kezhong Liu, Yuting Ma, Mozi Chen","doi":"10.1109/MOST57249.2023.00013","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00013","url":null,"abstract":"Emergency evacuation is critical following a ship accident, as passengers are required to escape the dynamic hazards and reach the muster station before the deadline. In the existing efforts, users are guided to a safe path away from the danger, but unconstrained detours may mislead users to miss the ship capsizing deadline. Another major drawback is the heavy congestion during crowd evacuation. Therefore, this paper proposes DC-HEN, a hierarchical emergency navigation algorithm with both deadline and congestion awareness for ship indoor environments. Taking advantage of reinforcement learning techniques, DC-HEN can provide an individually customized evacuation route for each user in a real-time manner. We validate the proposed approach in a large-scale simulation environment with different population sizes based on a real-ship indoor scenario. Compared with the state-of-the-art solutions (CANS, ECSSN), experimental results show that DC-HEN can trade off between path efficiency and congestion to guide users to the exit safely.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125726322","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}
Atsushi Kuribayashi, E. Takeuchi, Alexander Carballo, Yoshio Ishiguro, K. Takeda
{"title":"Intervention Request Planning with Operator Capability Model for Human-Automation Cooperative Recognition","authors":"Atsushi Kuribayashi, E. Takeuchi, Alexander Carballo, Yoshio Ishiguro, K. Takeda","doi":"10.1109/MOST57249.2023.00022","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00022","url":null,"abstract":"Human-automation cooperation in the recognition phase of the autonomous driving system (cooperative recognition) has been proposed to address the challenges in the conventional cooperation method, e.g., taking over vehicle control. In cooperative recognition, the operator intervenes in the recognition of obstacles and risks that are difficult for the automated system alone. To realize cooperation and maximize the performance of the overall cooperative system, human tasks must be carefully allocated taking into account human processing capability and state in addition to driving safety, efficiency, and comfort. Since the human states are not directly observable, we formulate this problem as a Partially Observable Markov Decision Process (POMDP). Through simulator experiments, we showed that designing reward functions in the POMDP model that are biased operator decisions leads to inappropriate intervention requests, and we presented a solution. Furthermore, the intervention request scheduled by the POMDP model was able to reduce the intervention request time while maintaining driving comfort compared to the myopic policy, which requests intervention from the closest target, and also the POMDP model could adapt to the operator’s state.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131081494","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}
{"title":"A Strategy for Boundary Adherence and Exploration in Black-Box Testing of Autonomous Vehicles","authors":"John M. Thompson, Quentin Goss, M. Akbaş","doi":"10.1109/MOST57249.2023.00028","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00028","url":null,"abstract":"The validation of artificial intelligence (AI) controlled vehicles is a vexing challenge. Black box testing of decision making in these vehicles has been used to abstract out the inner complexity of the AI. In scenario-based black box testing, the AI is placed within a scenario, and the input space for that scenario is explored. The fundamental metric of “how well tested the system is for that scenario” is based on the input state space coverage. Since most of these spaces have a high number of dimensions, it is critical to sample the state space efficiently and identify performance boundaries for the vehicle under test. In this paper, we propose a boundary adherence approach for autonomous vehicle validation that can explore the boundary between targeted and non-targeted behavior. This paper significantly improves and extends our previous approach that focused on generic black-box testing of AI systems by optimizing the algorithm itself, adding new tools for exploration, and applying the strategy to scenario-based AV testing. We provide an example regression of a scenario which illustrates the ability to model boundaries after they have been explored. Further results on higher dimensions show differing adherence strategies can improve exploration efficiency and how boundary exploration focuses on more “interesting” scenarios. Upon exploring the boundary, we found that predictions can be made about whether or not the system will result in targeted behavior.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128238257","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}
Balakrishnan Dharmalingam, Ibrahim Odat, Rajdeep Mukherjee, Brett Piggott, Anyi Liu
{"title":"Heterogeneous Generative Dataset for UASes","authors":"Balakrishnan Dharmalingam, Ibrahim Odat, Rajdeep Mukherjee, Brett Piggott, Anyi Liu","doi":"10.1109/MOST57249.2023.00034","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00034","url":null,"abstract":"In this poster, we present the construction of HGDAVE (Heterogeneous Generative Dataset for Unmanned Autonomous Systems), a new dataset for Connected and Autonomous Vehicles (CAVs) and Unmanned Aerial Vehicles (UAVs), namely Unmanned Autonomous Systems (UASes). The dataset will be used to train artificial intelligence (AI) models to detect cybersecurity and safety-related risks, malfunctions, and crashes. The dataset was collected from three sources: 1) script-generated flying or driving missions, 2) software fuzzer-generated crashes instances, and 3) cybersecurity exploits generated by ethical hackers. To collect the data, we utilized the Digital Twin (DT) to replicate the behavior of UASes, which provides data that can be used to analyze, develop, and detect new anomaly detection algorithms.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114605819","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}
{"title":"Copyright","authors":"","doi":"10.1109/most57249.2023.00003","DOIUrl":"https://doi.org/10.1109/most57249.2023.00003","url":null,"abstract":"","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115837902","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}
Bao Ming Ding, Yixin Huangfu, Haowen Zhang, Ching-Hung Tan, S. Habibi
{"title":"Enhanced Multiple DBSCAN Algorithm for Traffic Detection Using mmWave Radar","authors":"Bao Ming Ding, Yixin Huangfu, Haowen Zhang, Ching-Hung Tan, S. Habibi","doi":"10.1109/MOST57249.2023.00019","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00019","url":null,"abstract":"The ability to robustly and effectively detect and classify road objects is vital to an all-purpose traffic monitoring system. Recent development in mmWave radar technologies offers improved range and resolution at an affordable price, making it an ideal candidate for Intelligent Transportation System (ITS) applications. Modern mmWave radars output 3D detection point clouds representing moving objects. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is a popular method for clustering radar point clouds. However, our study found that several variations of DBSCAN perform less than expected in a road and intersection scene. To address this, we propose an Enhanced Multiple DBSCAN algorithm tailored specifically for traffic monitoring applications, which aims to improve detection performance using radar point cloud data. By using adaptive parameters, the Enhanced Multiple DBSCAN algorithm addresses the problem of reducing cluster size over distance. Additionally, a modified Non-Maximum Suppression (NMS) variation is included to address missed detections when merging results from multiple DBSCANs. Our Enhanced Multiple DBSCAN achieves over 90% precision in detecting road objects, the best result among all tested methods. The algorithms proposed and evaluated in this study provide a valuable reference for modern radar ITS applications.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132332496","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}
{"title":"Dual-Weight Particle Filter for Radar-Based Dynamic Bayesian Grid Maps","authors":"Max Peter Ronecker, M. Stolz, D. Watzenig","doi":"10.1109/MOST57249.2023.00027","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00027","url":null,"abstract":"Through constant improvements in recent years radar sensors have become a viable alternative to lidar as the main distancing sensor of an autonomous vehicle. Although robust and with the possibility to directly measure the radial velocity, it brings it’s own set of challenges, for which existing algorithms need to be adapted. One core algorithm of a perception system is dynamic occupancy grid mapping, which has traditionally relied on lidar. In this paper we present a dual-weight particle filter as an extension for a bayesian occupancy grid mapping framework to allow to operate it with radar as its main sensors. It uses two separate particle weights that are computed differently to compensate that a radial velocity measurement in many situations is not able to capture the actual velocity of an object. We evaluate the method extensively with simulated data and show the advantages over existing single weight solutions.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122726700","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}
Robin Karlsson, Alexander Carballo, Keisuke Fujii, Kento Ohtani, K. Takeda
{"title":"Predictive World Models from Real-World Partial Observations","authors":"Robin Karlsson, Alexander Carballo, Keisuke Fujii, Kento Ohtani, K. Takeda","doi":"10.1109/MOST57249.2023.00024","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00024","url":null,"abstract":"Cognitive scientists believe adaptable intelligent agents like humans perform reasoning through learned causal mental simulations of agents and environments. The problem of learning such simulations is called predictive world modeling. Recently, reinforcement learning (RL) agents leveraging world models have achieved SOTA performance in game environments. However, understanding how to apply the world modeling approach in complex real-world environments relevant to mobile robots remains an open question. In this paper, we present a framework for learning a probabilistic predictive world model for real-world road environments. We implement the model using a hierarchical VAE (HVAE) capable of predicting a diverse set of fully observed plausible worlds from accumulated sensor observations. While prior HVAE methods require complete states as ground truth for learning, we present a novel sequential training method to allow HVAEs to learn to predict complete states from partially observed states only. We experimentally demonstrate accurate spatial structure prediction of deterministic regions achieving 96.21 IoU, and close the gap to perfect prediction by 62 % for stochastic regions using the best prediction. By extending HVAEs to cases where complete ground truth states do not exist, we facilitate continual learning of spatial prediction as a step towards realizing explainable and comprehensive predictive world models for real-world mobile robotics applications. Code is available at https://github.com/robin-karlsson0/predictive-world-models.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"91 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116611801","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}
{"title":"RAMRL: Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning","authors":"G. Bagwe, Xiaoyong Yuan, Xianhao Chen, Lan Zhang","doi":"10.1109/MOST57249.2023.00011","DOIUrl":"https://doi.org/10.1109/MOST57249.2023.00011","url":null,"abstract":"Despite the success of AI-enabled onboard perception, on-ramp merging has been one of the main challenges for autonomous driving. Due to limited sensing range of onboard sensors, a merging vehicle can hardly observe main road conditions and merge properly. By leveraging the wireless communications between connected and automated vehicles (CAVs), a merging CAV has potential to proactively obtain the intentions of nearby vehicles. However, CAVs can be prone to inaccurate observations, such as the noisy basic safety messages (BSM) and poor quality surveillance images. In this paper, we present a novel approach for Robust on-ramp merge of CAVs via Augmented and Multi-modal Reinforcement Learning, named by RAMRL. Specifically, we formulate the on-ramp merging problem as a Markov decision process (MDP) by taking driving safety, comfort driving behavior, and traffic efficiency into account. To provide reliable merging maneuvers, we simultaneously leverage BSM and surveillance images for multi-modal observation, which is used to learn a policy model through proximal policy optimization (PPO). Moreover, to improve data efficiency and provide better generalization performance, we train the policy model with augmented data (e.g., noisy BSM and noisy surveillance images). Extensive experiments are conducted with Simulation of Urban MObility (SUMO) platform under two typical merging scenarios. Experimental results demonstrate the effectiveness and efficiency of our robust on-ramp merging design.","PeriodicalId":338621,"journal":{"name":"2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116236341","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}