Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed bas...Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method.To begin with,a trajectory prediction model is established based on the graph neural network(GNN)that is trained utilizing the INTERACTION dataset.Then,the validated trajectory prediction model is used to predict the future trajectories of surrounding road users,including pedestrians and vehicles.In addition,a GNN prediction model-enabled motion planner is developed based on the model predictive control technique.Furthermore,two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach,i.e.,merging and roundabout scenarios.The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.展开更多
Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adja...Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.展开更多
The new energy vehicle plays a crucial role in green transportation,and the energy management strategy of hybrid power systems is essential for ensuring energy-efficient driving.This paper presents a state-of-the-art ...The new energy vehicle plays a crucial role in green transportation,and the energy management strategy of hybrid power systems is essential for ensuring energy-efficient driving.This paper presents a state-of-the-art survey and review of reinforcement learning-based energy management strategies for hybrid power systems.Additionally,it envisions the outlook for autonomous intelligent hybrid electric vehicles,with reinforcement learning as the foundational technology.First of all,to provide a macro view of historical development,the brief history of deep learning,reinforcement learning,and deep reinforcement learning is presented in the form of a timeline.Then,the comprehensive survey and review are conducted by collecting papers from mainstream academic databases.Enumerating most of the contributions based on three main directions—algorithm innovation,powertrain innovation,and environment innovation—provides an objective review of the research status.Finally,to advance the application of reinforcement learning in autonomous intelligent hybrid electric vehicles,future research plans positioned as“Alpha HEV”are envisioned,integrating Autopilot and energy-saving control.展开更多
Bacteremia induced by periodontal infection is an important factor for periodontitis to threaten general health. P. gingivalis DNA/virulence factors have been found in the brain tissues from patients with Alzheimer’s...Bacteremia induced by periodontal infection is an important factor for periodontitis to threaten general health. P. gingivalis DNA/virulence factors have been found in the brain tissues from patients with Alzheimer’s disease(AD). The blood-brain barrier(BBB) is essential for keeping toxic substances from entering brain tissues. However, the effect of P. gingivalis bacteremia on BBB permeability and its underlying mechanism remains unclear. In the present study, rats were injected by tail vein with P. gingivalis three times a week for eight weeks to induce bacteremia. An in vitro BBB model infected with P. gingivalis was also established. We found that the infiltration of Evans blue dye and Albumin protein deposition in the rat brain tissues were increased in the rat brain tissues with P. gingivalis bacteremia and P. gingivalis could pass through the in vitro BBB model. Caveolae were detected after P. gingivalis infection in BMECs both in vivo and in vitro. Caveolin-1(Cav-1) expression was enhanced after P. gingivalis infection.Downregulation of Cav-1 rescued P. gingivalis-enhanced BMECs permeability. We further found P. gingivalis-gingipain could be colocalized with Cav-1 and the strong hydrogen bonding between Cav-1 and arg-specific-gingipain(RgpA) were detected.Moreover, P. gingivalis significantly inhibited the major facilitator superfamily domain containing 2a(Mfsd2a) expression. Mfsd2a overexpression reversed P. gingivalis-increased BMECs permeability and Cav-1 expression. These results revealed that Mfsd2a/Cav-1 mediated transcytosis is a key pathway governing BBB BMECs permeability induced by P. gingivalis, which may contribute to P. gingivalis/virulence factors entrance and the subsequent neurological impairments.展开更多
A comparative study of model predictive control(MPC)schemes and robust Hstate feedback control(RSC)method for trajectory tracking is proposed in this paper.The main objective of this paper is to compare MPC and RSC co...A comparative study of model predictive control(MPC)schemes and robust Hstate feedback control(RSC)method for trajectory tracking is proposed in this paper.The main objective of this paper is to compare MPC and RSC controllers’performance in tracking predefined trajectory under different scenarios.MPC controller is designed based on the simple longitudinal-yaw-lateral motions of a single-track vehicle with a linear tire,which is an approximation of the more realistic model of a vehicle with double-track motion with a non-linear tire mode.RSC is designed on the basis of the same method as adopted for the MPC controller to achieve a fair comparison.Then,three test cases are built in CarSim-Simulink joint platform.Specifically,the verification test is used to test the tracking accuracy of MPC and RSC controller under well road conditions.Besides,the double lane change test with low road adhesion is designed to find the maximum velocity that both controllers can carry out while guaranteeing stability.Furthermore,an extreme curve test is built where the road adhesion changes suddenly,in order to test the performance of both controllers under extreme conditions.Finally,the advantages and disadvantages of MPC and RSC under different scenarios are also discussed.展开更多
Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination...Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination of transferred deep learning and Gaussian process regression.General health indicators are extracted from the partial discharge process.The sequential degradation model of the health indicator is developed based on a deep learning framework and is migrated for the battery pack degradation prediction.The future degraded capacities of both battery pack and each battery cell are probabilistically predicted to provide a comprehensive lifetime prognostic.Besides,only a few separate battery cells in the source domain and early data of battery packs in the target domain are needed for model construction.Experimental results show that the lifetime prediction errors are less than 25 cycles for the battery pack,even with only 50 cycles for model fine-tuning,which can save about 90%time for the aging experiment.Thus,it largely reduces the time and labor for battery pack investigation.The predicted capacity trends of the battery cells connected in the battery pack accurately reflect the actual degradation of each battery cell,which can reveal the weakest cell for maintenance in advance.展开更多
Autonomous vehicles require safe motion planning in uncertain environments,which are largely caused by surrounding vehicles.In this paper,a driving environment uncertainty-aware motion planning framework is proposed t...Autonomous vehicles require safe motion planning in uncertain environments,which are largely caused by surrounding vehicles.In this paper,a driving environment uncertainty-aware motion planning framework is proposed to lower the risk of position uncertainty of surrounding vehicles with considering the risk of rollover.First,a 4-degree of freedom vehicle dynamics model,and a rollover risk index are introduced.Besides,the uncertainty of surrounding vehicles’position is processed and propagated based on the Extended Kalman Filter method.Then,the uncertainty potential field is established to handle the position uncertainty of autonomous vehicles.In addition,the model predictive controller is designed as the motion planning framework which accounts for the rollover risk,the position uncertainty of the surrounding vehicles,and vehicle dynamic constraints of autonomous vehicles.Furthermore,two edge cases,the cut-in scenario,and merging scenario are designed.Finally,the safety,effectiveness,and real-time performance of the proposed motion planning framework are demonstrated by employing a hardware-in-the-loop experiment bench.展开更多
Carbon nanofibers with a polygonal cross section (P-CNFs) synthesized using a catalytic chemical vapor deposition (CCVD) technology have been investigated for potential applications in lithium batteries as anode m...Carbon nanofibers with a polygonal cross section (P-CNFs) synthesized using a catalytic chemical vapor deposition (CCVD) technology have been investigated for potential applications in lithium batteries as anode materials. P-CNFs exhibit excellent high-rate capabilities. At a current density as high as 3.7 and 7.4 A/g, P-CNFs can still deliver a reversible capacity of 198.4 and 158.2 mAh/g, respectively. To improve their first coulombic efficiency, carbon-coated P-CNFs were prepared through thermal vapor deposition (TVD) of benzene at 900 ~C. The electrochemical results demonstrate that appropriate amount of carbon coating can improve the first coulombic efficiency, the cycling stability and the rate performance of P-CNFs. After carbon coating, P-CNFs gain a weight increase approximately by 103 wt%, with its first coulombic efficiency increasing from 63.1 to 78.4%, and deliver a reversible capacity of 197.4mAh/g at a current density of 3.7 A/g, After dozens of cycles, there is no significant capacity degradation at both low and high current densities.展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.52222215,52072051)Chongqing Municipal Natural Science Foundation of China(Grant No.CSTB2023NSCQ-JQX0003).
文摘Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method.To begin with,a trajectory prediction model is established based on the graph neural network(GNN)that is trained utilizing the INTERACTION dataset.Then,the validated trajectory prediction model is used to predict the future trajectories of surrounding road users,including pedestrians and vehicles.In addition,a GNN prediction model-enabled motion planner is developed based on the model predictive control technique.Furthermore,two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach,i.e.,merging and roundabout scenarios.The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.
基金supported by National Natural Science Foundation of China(52222215, 52272420, 52072051)。
文摘Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.
基金Supported by National Natural Science Foundation of China (Grant Nos.52222215,52072051)Fundamental Research Funds for the Central Universities in China (Grant No.2023CDJXY-025)Chongqing Municipal Natural Science Foundation of China (Grant No.CSTB2023NSCQ-JQX0003)。
文摘The new energy vehicle plays a crucial role in green transportation,and the energy management strategy of hybrid power systems is essential for ensuring energy-efficient driving.This paper presents a state-of-the-art survey and review of reinforcement learning-based energy management strategies for hybrid power systems.Additionally,it envisions the outlook for autonomous intelligent hybrid electric vehicles,with reinforcement learning as the foundational technology.First of all,to provide a macro view of historical development,the brief history of deep learning,reinforcement learning,and deep reinforcement learning is presented in the form of a timeline.Then,the comprehensive survey and review are conducted by collecting papers from mainstream academic databases.Enumerating most of the contributions based on three main directions—algorithm innovation,powertrain innovation,and environment innovation—provides an objective review of the research status.Finally,to advance the application of reinforcement learning in autonomous intelligent hybrid electric vehicles,future research plans positioned as“Alpha HEV”are envisioned,integrating Autopilot and energy-saving control.
基金supported by Scientific Research Funding Project of Education Department of Liaoning Province [grant number LJKZ0782]National Natural Science Foundation of China [grant numbers 81670999]。
文摘Bacteremia induced by periodontal infection is an important factor for periodontitis to threaten general health. P. gingivalis DNA/virulence factors have been found in the brain tissues from patients with Alzheimer’s disease(AD). The blood-brain barrier(BBB) is essential for keeping toxic substances from entering brain tissues. However, the effect of P. gingivalis bacteremia on BBB permeability and its underlying mechanism remains unclear. In the present study, rats were injected by tail vein with P. gingivalis three times a week for eight weeks to induce bacteremia. An in vitro BBB model infected with P. gingivalis was also established. We found that the infiltration of Evans blue dye and Albumin protein deposition in the rat brain tissues were increased in the rat brain tissues with P. gingivalis bacteremia and P. gingivalis could pass through the in vitro BBB model. Caveolae were detected after P. gingivalis infection in BMECs both in vivo and in vitro. Caveolin-1(Cav-1) expression was enhanced after P. gingivalis infection.Downregulation of Cav-1 rescued P. gingivalis-enhanced BMECs permeability. We further found P. gingivalis-gingipain could be colocalized with Cav-1 and the strong hydrogen bonding between Cav-1 and arg-specific-gingipain(RgpA) were detected.Moreover, P. gingivalis significantly inhibited the major facilitator superfamily domain containing 2a(Mfsd2a) expression. Mfsd2a overexpression reversed P. gingivalis-increased BMECs permeability and Cav-1 expression. These results revealed that Mfsd2a/Cav-1 mediated transcytosis is a key pathway governing BBB BMECs permeability induced by P. gingivalis, which may contribute to P. gingivalis/virulence factors entrance and the subsequent neurological impairments.
基金Supported by Natural Science Foundation of China(Grant Nos.52072051,51705044)Chongqing Municipal Natural Science Foundation of China(Grant No.cstc2020jcyj-msxmX0956)+1 种基金State Key Laboratory of Mechanical System and Vibration(Grant No.MSV202016)State Key Laboratory of Mechanical Transmissions(Grant No.SKLMT-KFKT-201806).
文摘A comparative study of model predictive control(MPC)schemes and robust Hstate feedback control(RSC)method for trajectory tracking is proposed in this paper.The main objective of this paper is to compare MPC and RSC controllers’performance in tracking predefined trajectory under different scenarios.MPC controller is designed based on the simple longitudinal-yaw-lateral motions of a single-track vehicle with a linear tire,which is an approximation of the more realistic model of a vehicle with double-track motion with a non-linear tire mode.RSC is designed on the basis of the same method as adopted for the MPC controller to achieve a fair comparison.Then,three test cases are built in CarSim-Simulink joint platform.Specifically,the verification test is used to test the tracking accuracy of MPC and RSC controller under well road conditions.Besides,the double lane change test with low road adhesion is designed to find the maximum velocity that both controllers can carry out while guaranteeing stability.Furthermore,an extreme curve test is built where the road adhesion changes suddenly,in order to test the performance of both controllers under extreme conditions.Finally,the advantages and disadvantages of MPC and RSC under different scenarios are also discussed.
基金Supported by National Natural Science Foundation of China(Grant Nos.51875054,U1864212)Graduate Research and Innovation Foundation of Chongqing+2 种基金China(Grant No.CYS20018)Chongqing Municipal Natural Science Foundation for Distinguished Young Scholars of China(Grant No.cstc2019jcyjjq X0016)Chongqing Science and Technology Bureau of China。
文摘Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination of transferred deep learning and Gaussian process regression.General health indicators are extracted from the partial discharge process.The sequential degradation model of the health indicator is developed based on a deep learning framework and is migrated for the battery pack degradation prediction.The future degraded capacities of both battery pack and each battery cell are probabilistically predicted to provide a comprehensive lifetime prognostic.Besides,only a few separate battery cells in the source domain and early data of battery packs in the target domain are needed for model construction.Experimental results show that the lifetime prediction errors are less than 25 cycles for the battery pack,even with only 50 cycles for model fine-tuning,which can save about 90%time for the aging experiment.Thus,it largely reduces the time and labor for battery pack investigation.The predicted capacity trends of the battery cells connected in the battery pack accurately reflect the actual degradation of each battery cell,which can reveal the weakest cell for maintenance in advance.
基金National Key R&D Program of China(Grant No.2020YFB1600303)National Natural Science Foundation of China(Grant Nos.U1964203,52072215)Chongqing Municipal Natural Science Foundation of China(Grant No.cstc2020jcyj-msxmX0956).
文摘Autonomous vehicles require safe motion planning in uncertain environments,which are largely caused by surrounding vehicles.In this paper,a driving environment uncertainty-aware motion planning framework is proposed to lower the risk of position uncertainty of surrounding vehicles with considering the risk of rollover.First,a 4-degree of freedom vehicle dynamics model,and a rollover risk index are introduced.Besides,the uncertainty of surrounding vehicles’position is processed and propagated based on the Extended Kalman Filter method.Then,the uncertainty potential field is established to handle the position uncertainty of autonomous vehicles.In addition,the model predictive controller is designed as the motion planning framework which accounts for the rollover risk,the position uncertainty of the surrounding vehicles,and vehicle dynamic constraints of autonomous vehicles.Furthermore,two edge cases,the cut-in scenario,and merging scenario are designed.Finally,the safety,effectiveness,and real-time performance of the proposed motion planning framework are demonstrated by employing a hardware-in-the-loop experiment bench.
基金financial support from the Ministry of Science and Technology of China(2011CB932604)
文摘Carbon nanofibers with a polygonal cross section (P-CNFs) synthesized using a catalytic chemical vapor deposition (CCVD) technology have been investigated for potential applications in lithium batteries as anode materials. P-CNFs exhibit excellent high-rate capabilities. At a current density as high as 3.7 and 7.4 A/g, P-CNFs can still deliver a reversible capacity of 198.4 and 158.2 mAh/g, respectively. To improve their first coulombic efficiency, carbon-coated P-CNFs were prepared through thermal vapor deposition (TVD) of benzene at 900 ~C. The electrochemical results demonstrate that appropriate amount of carbon coating can improve the first coulombic efficiency, the cycling stability and the rate performance of P-CNFs. After carbon coating, P-CNFs gain a weight increase approximately by 103 wt%, with its first coulombic efficiency increasing from 63.1 to 78.4%, and deliver a reversible capacity of 197.4mAh/g at a current density of 3.7 A/g, After dozens of cycles, there is no significant capacity degradation at both low and high current densities.