Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

A Novel Prescribed-Performance Path-Following Problem for Non-Holonomic Vehicles

The issue of achieving prescribed-performance path following in robotics is addressed in this paper,where the aim is to ensure that a desired path within a specified region is accu-rately converged to by the controlled vehicle.In this context,a novel form of the prescribed performance guiding vector field is introduced,accompanied by a prescribed-time sliding mode con-trol approach.Furthermore,the interdependence among the pre-scribed parameters is discussed.To validate the effectiveness of the proposed method,numerical simulations are presented to demonstrate the efficacy of the approach.

On-road vehicle verification based on VS-HOG and ELM

A solution is proposed for the real-time vehicle verification which is an important problem for numerous on- road vehicle applications. First, based on the vertical symmetry characteristics of vehicle images, a vertical symmetrical histograms of oriented gradients （VS-HOG） descriptor is proposed for extracting the image features. In the classification stage, an extreme learning machine （ELM） is used to improve the real-time performance. Experimental data demonstrate that, compared with other classical methods, the vehicle verification algorithm based on VS-HOG and ELM achieves a better trade-off between cost and performance. The computational cost is reduced by using the algorithm, while keeping the performance loss as low as possible. Furthermore, experimental results further show that the proposed vehicle verification method is suitable for on-road vehicle applications due to its better performance both in efficiency and accuracy.

Communication Resource-Efficient Vehicle Platooning Control With Various Spacing Policies

Platooning represents one of the key features that connected automated vehicles may possess as it allows multiple automated vehicles to be maneuvered cooperatively with small headways on roads. However, a critical challenge in accomplishing automated vehicle platoons is to deal with the effects of intermittent and sporadic vehicle-to-vehicle data transmissions caused by limited wireless communication resources. This paper addresses the co-design problem of dynamic event-triggered communication scheduling and cooperative adaptive cruise control for a convoy of automated vehicles with diverse spacing policies. The central aim is to achieve automated vehicle platooning under various gap references with desired platoon stability and spacing performance requirements, while simultaneously improving communication efficiency. Toward this aim, a dynamic event-triggered scheduling mechanism is developed such that the intervehicle data transmissions are scheduled dynamically and efficiently over time. Then, a tractable co-design criterion on the existence of both the admissible event-driven cooperative adaptive cruise control law and the desired scheduling mechanism is derived. Finally, comparative simulation results are presented to substantiate the effectiveness and merits of the obtained results.

A blockchain based privacy-preserving federated learning scheme for Internet of Vehicles

The application of artificial intelligence technology in Internet of Vehicles(lov)has attracted great research interests with the goal of enabling smart transportation and traffic management.Meanwhile,concerns have been raised over the security and privacy of the tons of traffic and vehicle data.In this regard,Federated Learning(FL)with privacy protection features is considered a highly promising solution.However,in the FL process,the server side may take advantage of its dominant role in model aggregation to steal sensitive information of users,while the client side may also upload malicious data to compromise the training of the global model.Most existing privacy-preserving FL schemes in IoV fail to deal with threats from both of these two sides at the same time.In this paper,we propose a Blockchain based Privacy-preserving Federated Learning scheme named BPFL,which uses blockchain as the underlying distributed framework of FL.We improve the Multi-Krum technology and combine it with the homomorphic encryption to achieve ciphertext-level model aggregation and model filtering,which can enable the verifiability of the local models while achieving privacy-preservation.Additionally,we develop a reputation-based incentive mechanism to encourage users in IoV to actively participate in the federated learning and to practice honesty.The security analysis and performance evaluations are conducted to show that the proposed scheme can meet the security requirements and improve the performance of the FL model.

Reliability evaluation of IGBT power module on electric vehicle using big data

There are challenges to the reliability evaluation for insulated gate bipolar transistors(IGBT)on electric vehicles,such as junction temperature measurement,computational and storage resources.In this paper,a junction temperature estimation approach based on neural network without additional cost is proposed and the lifetime calculation for IGBT using electric vehicle big data is performed.The direct current(DC)voltage,operation current,switching frequency,negative thermal coefficient thermistor(NTC)temperature and IGBT lifetime are inputs.And the junction temperature(T_(j))is output.With the rain flow counting method,the classified irregular temperatures are brought into the life model for the failure cycles.The fatigue accumulation method is then used to calculate the IGBT lifetime.To solve the limited computational and storage resources of electric vehicle controllers,the operation of IGBT lifetime calculation is running on a big data platform.The lifetime is then transmitted wirelessly to electric vehicles as input for neural network.Thus the junction temperature of IGBT under long-term operating conditions can be accurately estimated.A test platform of the motor controller combined with the vehicle big data server is built for the IGBT accelerated aging test.Subsequently,the IGBT lifetime predictions are derived from the junction temperature estimation by the neural network method and the thermal network method.The experiment shows that the lifetime prediction based on a neural network with big data demonstrates a higher accuracy than that of the thermal network,which improves the reliability evaluation of system.

Distributed Platooning Control of Automated Vehicles Subject to Replay Attacks Based on Proportional Integral Observers

Secure platooning control plays an important role in enhancing the cooperative driving safety of automated vehicles subject to various security vulnerabilities.This paper focuses on the distributed secure control issue of automated vehicles affected by replay attacks.A proportional-integral-observer(PIO)with predetermined forgetting parameters is first constructed to acquire the dynamical information of vehicles.Then,a time-varying parameter and two positive scalars are employed to describe the temporal behavior of replay attacks.In light of such a scheme and the common properties of Laplace matrices,the closed-loop system with PIO-based controllers is transformed into a switched and time-delayed one.Furthermore,some sufficient conditions are derived to achieve the desired platooning performance by the view of the Lyapunov stability theory.The controller gains are analytically determined by resorting to the solution of certain matrix inequalities only dependent on maximum and minimum eigenvalues of communication topologies.Finally,a simulation example is provided to illustrate the effectiveness of the proposed control strategy.

A credibility-aware swarm-federated deep learning framework in internet of vehicles

Although Federated Deep Learning(FDL)enables distributed machine learning in the Internet of Vehicles(IoV),it requires multiple clients to upload model parameters,thus still existing unavoidable communication overhead and data privacy risks.The recently proposed Swarm Learning(SL)provides a decentralized machine learning approach for unit edge computing and blockchain-based coordination.A Swarm-Federated Deep Learning framework in the IoV system(IoV-SFDL)that integrates SL into the FDL framework is proposed in this paper.The IoV-SFDL organizes vehicles to generate local SL models with adjacent vehicles based on the blockchain empowered SL,then aggregates the global FDL model among different SL groups with a credibility weights prediction algorithm.Extensive experimental results show that compared with the baseline frameworks,the proposed IoV-SFDL framework reduces the overhead of client-to-server communication by 16.72%,while the model performance improves by about 5.02%for the same training iterations.

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

To address the challenges of high complexity,poor real-time performance,and low detection rates for small target vehicles in existing vehicle object detection algorithms,this paper proposes a real-time lightweight architecture based on You Only Look Once(YOLO)v5m.Firstly,a lightweight upsampling operator called Content-Aware Reassembly of Features(CARAFE)is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles,reducing the missed detection rate and false detection rate.Secondly,a new prediction layer for tiny targets is added,and the feature fusion network is redesigned to enhance the detection capability for small targets.Finally,this paper applies L1 regularization to train the improved network,followed by pruning and fine-tuning operations to remove redundant channels,reducing computational and parameter complexity and enhancing the detection efficiency of the network.Training is conducted on the VisDrone2019-DET dataset.The experimental results show that the proposed algorithmreduces parameters and computation by 63.8% and 65.8%,respectively.The average detection accuracy improves by 5.15%,and the detection speed reaches 47 images per second,satisfying real-time requirements.Compared with existing approaches,including YOLOv5m and classical vehicle detection algorithms,our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.

Anti-Byzantine Attacks Enabled Vehicle Selection for Asynchronous Federated Learning in Vehicular Edge Computing

In vehicle edge computing(VEC),asynchronous federated learning(AFL)is used,where the edge receives a local model and updates the global model,effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles,renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model,and the vehicle may also be affected by Byzantine attacks,leading to the deterioration of the vehicle data.However,based on deep reinforcement learning(DRL),we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL.At the same time,when aggregating AFL,we can focus on those vehicles with better performance to improve the accuracy and safety of the system.In this paper,we proposed a vehicle selection scheme based on DRL in VEC.In this scheme,vehicle’s mobility,channel conditions with temporal variations,computational resources with temporal variations,different data amount,transmission channel status of vehicles as well as Byzantine attacks were taken into account.Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.

A method to interpret fracture aperture of rock slope using adaptive shape and unmanned aerial vehicle multi-angle nap-of-the-object photogrammetry

The aperture of natural rock fractures significantly affects the deformation and strength properties of rock masses,as well as the hydrodynamic properties of fractured rock masses.The conventional measurement methods are inadequate for collecting data on high-steep rock slopes in complex mountainous regions.This study establishes a high-resolution three-dimensional model of a rock slope using unmanned aerial vehicle(UAV)multi-angle nap-of-the-object photogrammetry to obtain edge feature points of fractures.Fracture opening morphology is characterized using coordinate projection and transformation.Fracture central axis is determined using vertical measuring lines,allowing for the interpretation of aperture of adaptive fracture shape.The feasibility and reliability of the new method are verified at a construction site of a railway in southeast Tibet,China.The study shows that the fracture aperture has a significant interval effect and size effect.The optimal sampling length for fractures is approximately 0.5e1 m,and the optimal aperture interpretation results can be achieved when the measuring line spacing is 1%of the sampling length.Tensile fractures in the study area generally have larger apertures than shear fractures,and their tendency to increase with slope height is also greater than that of shear fractures.The aperture of tensile fractures is generally positively correlated with their trace length,while the correlation between the aperture of shear fractures and their trace length appears to be weak.Fractures of different orientations exhibit certain differences in their distribution of aperture,but generally follow the forms of normal,log-normal,and gamma distributions.This study provides essential data support for rock and slope stability evaluation,which is of significant practical importance.

Ensuring Secure Platooning of Constrained Intelligent and Connected Vehicles Against Byzantine Attacks:A Distributed MPC Framework

This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control framework for such ICVs.This framework seamlessly integrates the predesigned optimal control with distributed model predictive control(DMPC)optimization and introduces a unique distributed attack detector to ensure the reliability of the transmitted information among vehicles.Notably,our strategy uses previously broadcasted information and a specialized convex set,termed the“resilience set”,to identify unreliable data.This approach significantly eases graph robustness prerequisites,requiring only an(F+1)-robust graph,in contrast to the established mean sequence reduced algorithms,which require a minimum(2F+1)-robust graph.Additionally,we introduce a verification algorithm to restore trust in vehicles under minor attacks,further reducing communication network robustness.Our analysis demonstrates the recursive feasibility of the DMPC optimization.Furthermore,the proposed method achieves exceptional control performance by minimizing the discrepancies between the DMPC control inputs and predesigned platoon control inputs,while ensuring constraint compliance and cybersecurity.Simulation results verify the effectiveness of our theoretical findings.

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Experimental Study on Occupant's Thermal Responses under the Non-uniform Conditions in Vehicle Cabin during the Heating Period

The existing investigations on thermal comfort mostly focus on the thermal environment conditions, especially of the air-flow field and the temperature distributions in vehicle cabin. Less attention appears to direct to the thermal comfort or thermal sensation of occupants, even to the relationship between thermal conditions and thermal sensation. In this paper, a series of experiments were designed and conducted for understanding the non-uniform conditions and the occupant＇s thermal responses in vehicle cabin during the heating period. To accurately assess the transient temperature distribution in cabin in common daily condition, the air temperature at a number of positions is measured in a full size vehicle cabin under natural winter environment in South China by using a discrete thermocouples network. The occupant body is divided into nine segments, the skin temperature at each segment and the occupant＇s local thermal sensation at the head, body, upper limb and lower limb are monitored continuously. The skin temperature is observed by using a discrete thermocouples network, and the local thermal sensation is evaluated by using a seven-point thermal comfort survey questionnaire proposed by American Society of Heating, Refrigerating and Air-Conditioning Engineers, Inc（ASHRAE） Standard. The relationship between the skin temperature and the thermal sensation is discussed and regressed by statistics method. The results show that the interior air temperature is highly non-uniform over the vehicle cabin. The locations where the occupants sit have a significant effect on the occupant＇s thermal responses, including the skin temperature and the thermal sensation. The skin temperaWa-e and thermal sensation are quite different between body segments due to the effect of non-uniform conditions, clothing resistance, and the human thermal regulating system. A quantitative relationship between the thermal sensation and the skin temperature at each body segment of occupant in real life traffic is presented. The investigation result indicates that the skin temperature is a robust index to evaluate the thermal sensation. Applying the skin temperature to designing and controlling parameters of the heating, ventilation and air conditioning（HVAC） system may benefit the thermal comfort and reducing energy consumption.

Path-Following Control With Obstacle Avoidance of Autonomous Surface Vehicles Subject to Actuator Faults

This paper investigates the path-following control problem with obstacle avoidance of autonomous surface vehicles in the presence of actuator faults,uncertainty and external disturbances.Autonomous surface vehicles inevitably suffer from actuator faults in complex sea environments,which may cause existing obstacle avoidance strategies to fail.To reduce the influence of actuator faults,an improved artificial potential function is constructed by introducing the lower bound of actuator efficiency factors.The nonlinear state observer,which only depends on measurable position information of the autonomous surface vehicle,is used to address uncertainties and external disturbances.By using a backstepping technique and adaptive mechanism,a path-following control strategy with obstacle avoidance and fault tolerance is designed which can ensure that the tracking errors converge to a small neighborhood of zero.Compared with existing results,the proposed control strategy has the capability of obstacle avoidance and fault tolerance simultaneously.Finally,the comparison results through simulations are given to verify the effectiveness of the proposed method.

A landslide monitoring method using data from unmanned aerial vehicle and terrestrial laser scanning with insufficient and inaccurate ground control points

Non-contact remote sensing techniques,such as terrestrial laser scanning(TLS)and unmanned aerial vehicle(UAV)photogrammetry,have been globally applied for landslide monitoring in high and steep mountainous areas.These techniques acquire terrain data and enable ground deformation monitoring.However,practical application of these technologies still faces many difficulties due to complex terrain,limited access and dense vegetation.For instance,monitoring high and steep slopes can obstruct the TLS sightline,and the accuracy of the UAV model may be compromised by absence of ground control points(GCPs).This paper proposes a TLS-and UAV-based method for monitoring landslide deformation in high mountain valleys using traditional real-time kinematics(RTK)-based control points(RCPs),low-precision TLS-based control points(TCPs)and assumed control points(ACPs)to achieve high-precision surface deformation analysis under obstructed vision and impassable conditions.The effects of GCP accuracy,GCP quantity and automatic tie point(ATP)quantity on the accuracy of UAV modeling and surface deformation analysis were comprehensively analyzed.The results show that,the proposed method allows for the monitoring accuracy of landslides to exceed the accuracy of the GCPs themselves by adding additional low-accuracy GCPs.The proposed method was implemented for monitoring the Xinhua landslide in Baoxing County,China,and was validated against data from multiple sources.

Quaternion-based Nonlinear Trajectory Tracking Control of a Quadrotor Unmanned Aerial Vehicle

At present, most controllers of quadrotor unmanned aerial vehicles（UAVs） use Euler angles to express attitude. These controllers suffer a singularity problem when the pitch angle is near 90°, which limits the maneuverability of the UAV. To overcome this problem, based on the quatemion attitude representation, a 6 degree of freedom（DOF） nonlinear controller of a quadrotor UAV is designed using the trajectory linearization control（TLC） method. The overall controller contains a position sub-controller and an attitude sub-controller. The two controllers regulate the translational and rotational motion of the UAV, respectively. The controller is improved by using the commanded value instead of the nominal value as the input of the inner control loop. The performance of controller is tested by simulation before and after the improvement, the results show that the improved controller is better. The proposed controller is also tested via numerical simulation and real flights and is compared with the traditional controller based on Euler angles. The test results confirm the feasibility and the robustness of the proposed nonlinear controller. The proposed controller can successfully solve the singularity problem that usually occurs in the current attitude control of UAV and it is easy to be realized.

Vision-based long-distance lane perception and front vehicle location for full autonomous vehicles on highway roads

A new vision-based long-distance lane perception and front vehicle location method was developed for decision making of full autonomous vehicles on highway roads,Firstly,a real-time long-distance lane detection approach was presented based on a linear-cubic road model for two-lane highways.By using a novel robust lane marking feature which combines the constraints of intensity,edge and width,the lane markings in far regions were extracted accurately and efficiently.Next,the detected lane lines were selected and tracked by estimating the lateral offset and heading angle of ego vehicle with a Kalman filter,Finally,front vehicles were located on correct lanes using the tracked lane lines,Experiment results show that the proposed lane perception approach can achieve an average correct detection rate of 94.37% with an average false positive detection rate of 0.35%,The proposed approaches for long-distance lane perception and front vehicle location were validated in a 286 km full autonomous drive experiment under real traffic conditions.This successful experiment shows that the approaches are effective and robust enough for full autonomous vehicles on highway roads.

Robust Attitude Control for Reusable Launch Vehicles Based on Fractional Calculus and Pigeon-inspired Optimization

In this paper, a robust attitude control system based on fractional order sliding mode control and dynamic inversion approach is presented for the reusable launch vehicle RLV during the reentry phase. By introducing the fractional order sliding surface to replace the integer order one, we design robust outer loop controller to compensate the error introduced by inner loop controller designed by dynamic inversion approach. To take the uncertainties of aerodynamic parameters into account, stochastic robustness design approach based on the Monte Carlo simulation and Pigeon-inspired optimization is established to increase the robustness of the controller. Some simulation results are given out which indicate the reliability and effectiveness of the attitude control system. © 2014 Chinese Association of Automation.

Characterization of on-road CO, HC and NO emissions for petrol vehicle fleet in China city

Vehicle emissions are a major source of air pollution in urban areas. The impact on urban air quality could be reduced if the trends of vehicle emissions are well understood. In the present study, the real-world emissions of vehicles were measured using a remote sensing system at five sites in Hangzhou, China from February 2004 to August 2005. More than 48000 valid gasoline powered vehicle emissions of carbon monoxide （CO）, hydrocarbons （HC） and nitrogen oxide （NO） were measured. The results show that petrol vehicle fleet in Hangzhou has considerably high CO emissions, with the average emission concentration of 2.71 %±0.02%, while HC and NO emissions are relatively lower, with the average emission concentration of （153.72±1.16）×10-6 and （233.53±1.80）×10-6, respectively. Quintile analysis of both average emission concentration and total amount emissions by model year suggests that in-use emission differences between well maintained and badly maintained vehicles are larger than the age-dependent deterioration of emissions. In addition, relatively new high polluting vehicles are the greatest contributors to fleet emissions with, for example, 46.55% of carbon monoxide fleet emissions being produced by the top quintile high emitting vehicles from model years 2000-2004. Therefore, fleet emissions could be significantly reduced if new highly polluting vehicles were subject to effective emissions testing followed by appropriate remedial action.