Pedestrian Collision Avoidance Research Articles

Simulating pedestrian avoidance: The human-zombie game.

This study introduces a simulated active matter system, applying the pedestrian collision avoidance paradigm, which involves dynamically adjusting the desired velocity. We present a human-zombie game set within a closed geometry, combining predator-prey behavior with a one-way contagion process that transforms prey into predators. The system demonstrates varied responses in our implemented model: with agents having the same maximum speeds, a single zombie always captures a human, whereas two zombies never capture a single human agent. As the number of human agents increases, observables such as the final fraction of zombie agents and total conversion times exhibit significant changes in the system's behavior at intermediate density values. Most notably, there is evidence of a first-order phase transition when analyzing the mean population speed as an order parameter.

Camera-in-the-loop based test scenario generation method for pedestrian collision avoidance system

The Pedestrian Collision Avoidance System (PCAS) of Intelligent Vehicle (IV) can be effective in preventing the occurrence of traffic accidents. However, the complicated operation environments introduce great challenges to the camera used by the PCAS. Therefore, the camera based PCAS should be fully tested and evaluated before deployment. The traditional simulation test for the camera based PCAS attempted to use geometric or physical simulation models, which have low reality and are suitable for the primary stage of the PCAS development. Camera-in-the-Loop (CIL) test is one of Hardware-in-the-Loop methods that embeds the real camera hardware into the virtual simulation system to test the camera. CIL can utilize the real hardware response while overcoming the common simulation weakness of fidelity. In this paper, we construct a CIL test platform, and propose the CIL based test scenarios generation and scenario parameter impact evaluation method for PCAS. First, we construct the CIL test platform whose image quality and functional confidence are both validated to prove CIL credibility. Second, the PCAS under the test is analyzed and the corresponding test scenario parameters are designed. In order to accelerate the test scenario generation, a Greedy Based Combination test method (GBC) based on the CIL is proposed. The Chi-square analysis and two-factor of variance analysis verification methods are used to analyze the influence of individual and multiple scenario parameters on the PCAS performance. The experiment results show that the GBC improves the test speed by 12 times compared to the traversal test, and the frequency ratio of each scenario parameter is no more than 3% different from that of the traversal test. Also, GBC has an equivalent ability to find the PCAS collision scenarios parameter combination to the traversal test.

Modeling Lateral Control Behavior of Driver for Manual Takeover of Automated Vehicles During Pedestrian Collision Avoidance

Modeling Lateral Control Behavior of Driver for Manual Takeover of Automated Vehicles During Pedestrian Collision Avoidance

Improved social force model based on pedestrian collision avoidance behavior in counterflow

The social force model is a widely used microscopic model for reproducing pedestrian behaviors. However, the traditional social force model lack consideration for pedestrian collision avoidance behaviors, such as the significant impact on model accuracy in scenarios like pandemics. In this study, we introduce a novel avoidance force component to the social force model to capture pedestrian collision avoidance behavior within counterflow. We conducted bidirectional pedestrian control experiments during the pandemic, directly tracking pedestrian movement trajectories and spatiotemporal characteristics. Key parameters were extracted and used to calibrate the model based on collision avoidance scenarios among pedestrians. Furthermore, we compared the performance of our proposed model with previous model research and experiments by using individual crossing time and order parameter as evaluation parameters. These findings provide an efficient tool for future applications that can realistically model pedestrian counterflow under conditions where pedestrian collision avoidance behavior is significantly pronounced.

Pedestrian Collision Avoidance in Autonomous Vehicles: A Review

Pedestrian collision avoidance is a crucial task in the development and democratization of autonomous vehicles. The aim of this review is to provide an accessible overview of the pedestrian collision avoidance systems in autonomous vehicles that have been proposed by the scientific community over the last ten years. For this purpose, we propose a classification of studies in the literature in terms of the following: (i) pedestrian detection methods, (ii) collision avoidance approaches, (iii) actions, (iv) computing methods, and (v) test methods.

Development of pedestrian collision avoidance strategy based on the fusion of Markov and social force models

Abstract. In urban traffic, accurate prediction of pedestrian trajectory and advanced collision avoidance strategy can effectively reduce the collision risk between intelligent vehicles and pedestrians. In order to improve the prediction accuracy of pedestrian trajectory and the safety of collision avoidance, a longitudinal and lateral intelligent collision avoidance strategy based on pedestrian trajectory prediction is proposed. Firstly, the process of a pedestrian crossing the road is considered as a combination of free motion described by first-order Markov model and the constrained motion presented by improved social force model. The predicted pedestrian trajectory is obtained by weighted fusion of the trajectories of the two models with a multiple linear regression algorithm. Secondly, according to the predicted pedestrian trajectory and time to collision (TTC) the longitudinal and lateral collision avoidance strategy is designed. The improved artificial potential field method is used to plan the lateral collision avoidance path in real time based on the predicted pedestrian position, and a fuzzy controller is constructed to obtain the desired deceleration of the vehicle. Finally, the pedestrian motion fusion model and the longitudinal and lateral collision avoidance strategy are verified by Prescan and Simulink co-simulation. The results show that the average displacement error (ADE) and final displacement error (FDE) of pedestrian trajectory based on pedestrian motion fusion model are smaller compared with a Markov model and improved social force model, and the proposed pedestrian collision avoidance strategy can effectively achieve longitudinal and lateral collision avoidance.

Future pedestrian location prediction in first-person videos for autonomous vehicles and social robots

Future pedestrian trajectory prediction in first-person videos offers great prospects to help autonomous vehicles and social robots to enable better human-vehicle interactions. Given an egocentric video stream, we aim to predict the location and depth (distance between the observed person and the camera) of his/her neighbors in future frames. To locate their future trajectories, we mainly consider three main factors: a) It is necessary to restore the spatial distribution of pedestrians in 2D image to 3D space, i.e., to extract the distance between the pedestrian and the camera which is often neglected. b) It is critical to utilize neighbors’ poses to recognize their intentions. c) It is important to learn human-vehicle interactions from the pedestrian’s historical trajectories. We propose to incorporate these three factors into a multi-channel tensor to represent the main features in real-life 3D space. We then put this tensor into an innovative end-to-end fully convolutional network based on transformer architecture. Experimental results reveal our method outperforms other state-of-the-art methods on public benchmarks MOT15, MOT16 and MOT17. The proposed method will be useful to understand human-vehicle interaction and helpful for pedestrian collision avoidance.

Fuzzy Logic Approaches for Pedestrian Collision Avoidance in Intelligent Vehicles

Fuzzy Logic Approaches for Pedestrian Collision Avoidance in Intelligent Vehicles

Vehicle Path Planning Based on Pedestrian Collision Avoidance Action

Vehicle Path Planning Based on Pedestrian Collision Avoidance Action

Obtaining Pedestrian Interest Regions Using Experimental Methods

In pedestrian simulation, using the region of interest of pedestrians can solve the problem of data redundancy and complexity and lack of representation in the pedestrian saccade range, and establish an efficient pedestrian collision avoidance behavior model. The real-time eye movement data of unidirectional and bidirectional pedestrian flow were collected by eye tracker, and the mathematical models of pedestrian flow density, radius and angle of each region of interest were established. Analyzing the experimental data, it is found that the range of pedestrian interest region is affected by pedestrian density. The angle of the pedestrian interest region is generally not more than 90°, and the radius of the high-interest region and the low-interest region are negatively correlated with the pedestrian density. When the pedestrian density reaches a certain degree, the radius of the high-interest region and the low-interest region approach the fixed value respectively.

Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning.

Deep neural network-based systems are now state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs (from noise or adversarial examples) are often enough to change network-based decisions, which was recently shown to cause an autonomous vehicle to swerve into another lane. In light of these dangers, numerous algorithms have been developed as defensive mechanisms from these adversarial inputs, some of which provide formal robustness guarantees or certificates. This work leverages research on certified adversarial robustness to develop an online certifiably robust for deep reinforcement learning algorithms. The proposed defense computes guaranteed lower bounds on state-action values during execution to identify and choose a robust action under a worst case deviation in input space due to possible adversaries or noise. Moreover, the resulting policy comes with a certificate of solution quality, even though the true state and optimal action are unknown to the certifier due to the perturbations. The approach is demonstrated on a deep Q-network (DQN) policy and is shown to increase robustness to noise and adversaries in pedestrian collision avoidance scenarios, a classic control task, and Atari Pong. This article extends our prior work with new performance guarantees, extensions to other reinforcement learning algorithms, expanded results aggregated across more scenarios, an extension into scenarios with adversarial behavior, comparisons with a more computationally expensive method, and visualizations that provide intuition about the robustness algorithm.

Optimization of Emergency Braking Pedestrian Collision Avoidance for Autonomous Vehicle Fusing the Fuzzy Neural Network with the Genetic Algorithm

Optimization of Emergency Braking Pedestrian Collision Avoidance for Autonomous Vehicle Fusing the Fuzzy Neural Network with the Genetic Algorithm

An exploratory study of drivers’ EEG response during emergent collision avoidance

Introduction: EEG (electroencephalogram) has been applied as a valuable measure to estimate drivers’ mental status and cognitive workload during driving tasks. However, most previous studies have focused on the EEG features at particular driver status, such as fatigue or distraction, with less attention paid to EEG response in emergent and safety–critical situations. This study aims to investigate the underlying patterns of different EEG components during an emergent collision avoidance process. Method: A driving simulator experiment was conducted with 38 participants (19 females and 19 males). The scenario included a roadside pedestrian who suddenly crossed the road when the driver approached. The participants’ EEG data were collected during the pedestrian-collision avoidance process. The log-transformed power and power ratio of four typical EEG components (i.e., delta, theta, alpha and beta) were extracted from four collision avoidance stages: Stage 1-normal driving stage, Stage 2-hazard perception stage, Stage 3-evasive action stage, and Stage 4-post-hazard stage. Results: The activities of all four EEG bands changed consistently during the collision avoidance process, with the power increased significantly from Stage 1 to Stage 4. Drivers who collided with the pedestrian and drivers who avoided the collision successfully did not show a significant difference in EEG activity across the stages. Male drivers had a higher delta power ratio and lower alpha power ratio than females in both hazard perception and evasive action stages. Conclusions: Enhanced activities of different EEG bands could be concurrent at emergent and safety–critical situations. Female drivers were more mentally aroused than male drivers during the collision avoidance process. Practical Applications: The study generates more understanding of drivers’ neurophysiological response in an emergent and safety–critical collision avoidance event. Driver state monitoring and warning systems that aim to assist drivers in impending collisions may utilize the patterns of EEG activity identified in the collision avoidance process.

Automated Braking Decision and Control for Pedestrian Collision Avoidance Based on Risk Assessment

Automated Braking Decision and Control for Pedestrian Collision Avoidance Based on Risk Assessment

Pedestrian Collision Risk Assessment Based on State Estimation and Motion Prediction

Active pedestrian collision avoidance (APCA) systems can significantly reduce road injuries and thus have attracted considerable attention from both the automobile and the transportation industries. Numerous studies have focused on APCA; however, it remains challenging to model variable and complex scenarios in a safe, efficient and low-cost way. For this purpose, this paper proposes a novel multipedestrian collision risk assessment framework comprising a motion prediction module, a collision checking module and a collision risk assessment module. First, the motion of the ego vehicle (EV) is predicted through a constant-acceleration (V-CA) model and a constant-turn-rate and constant-velocity (V-CTRV) model in different scenarios. Next, the pedestrian motion is estimated using Kalman filter (KF) approaches based on a constant-velocity (PCV) model and a constant-acceleration (P-CA) model. Then, the potential collision area (PCA) is defined according to the predicted motions of the EV and pedestrian, and the time-to collision (TTC) is selected to conduct collision checking. Finally, the most dangerous pedestrian is identified as the target with the minimum TTC in a multipedestrian scenario, and field tests are conducted on an autonomous vehicle platform. Comparative simulations indicate that the P-CA-based KF is more accurate and robust in variable-velocity scenarios than the P-CV-based KF. Furthermore, multipedestrian scenario simulations validate the effectiveness of the proposed framework.

Prediction of stopping distance for autonomous emergency braking using stereo camera pedestrian detection

Autonomous vehicle (AV) attracts a lot of research interest because of their ability to reduce road fatalities and save people's lives. Pedestrian detection and collision avoidance are the crucial parts of AVs. The existing pedestrian detection systems don't guarantee better accuracy under complex scenarios, poor light conditions, and low complexity overhead. Moreover, these systems rely on monocular camera object detection. Hence, this paper aims to propose a stereo-vision based pedestrian detection and collision avoidance system for AVs. It uses two cameras fixed at a specific distance apart to scan the environment. Once a pedestrian is detected, the system calculates the distance. The Automatic Emergency Braking System (AEBS) controller algorithm will activate the AEB if the estimated distance is less than 3.3 m, considered safe. MATLAB is used for the implementation, and the experimental results reveal that the proposed method is promising in terms of prediction accuracy and minimizing fatalities.

Surface Electromyography-Controlled Pedestrian Collision Avoidance: A Driving Simulator Study

Drivers with disabilities such as hemiplegia or unilateral upper limb amputation restricting steering wheel operation to one arm could encounter the challenge of stabilizing vehicles during pedestrian collision avoidance. An sEMG-controlled steering assistance system was developed for these drivers to enable rapid steering wheel rotation with only one healthy arm. Test drivers were recruited to use the Myo armband as a sEMG-based interface to perform pedestrian collision avoidance in a driving simulator. It was hypothesized that the sEMG-based interface would be comparable or superior in vehicle stability to manual takeover from automated driving and conventional steering wheel operation. The Myo armband interface was significantly superior to manual takeover from automated driving and comparable to manual steering wheel operation. The results of the driving simulator trials confirm the feasibility of the sEMG-controlled system as a safe alternative that could benefit drivers with the aforesaid disabilities.

The Perception System of Intelligent Ground Vehicles in All Weather Conditions: A Systematic Literature Review.

Perception is a vital part of driving. Every year, the loss in visibility due to snow, fog, and rain causes serious accidents worldwide. Therefore, it is important to be aware of the impact of weather conditions on perception performance while driving on highways and urban traffic in all weather conditions. The goal of this paper is to provide a survey of sensing technologies used to detect the surrounding environment and obstacles during driving maneuvers in different weather conditions. Firstly, some important historical milestones are presented. Secondly, the state-of-the-art automated driving applications (adaptive cruise control, pedestrian collision avoidance, etc.) are introduced with a focus on all-weather activity. Thirdly, the most involved sensor technologies (radar, lidar, ultrasonic, camera, and far-infrared) employed by automated driving applications are studied. Furthermore, the difference between the current and expected states of performance is determined by the use of spider charts. As a result, a fusion perspective is proposed that can fill gaps and increase the robustness of the perception system.

Collision Avoidance of Low Speed Autonomous Shuttles with Pedestrians

This paper is on a pedestrian collision avoidance system for low speed autonomous shuttles based on Vehicle-to-Pedestrian (V2P) communication. When pedestrians cannot be detected using line-of-sight sensors like camera, radar and LIDAR, V2P communication with the Dedicated Short Range Communication (DSRC) enabled pedestrian smartphone is used to detect and localize them through the in-vehicle DSRC radio used for Vehicle-to-Everything (V2X) communication. The vehicle, then, either stops or, if possible, goes around the pedestrian in a socially acceptable manner using the elastic band method for locally modifying the vehicle trajectory in real time. The elastic band method of collision avoidance is modified for fast real time execution in this paper. Along with model-in-the-loop simulations, a hardware-in-the-loop simulator using an automated driving vehicle model in the high fidelity vehicle dynamics simulation program Carsim Real Time with Sensors and Traffic with two DSRC modems emulating the vehicle and pedestrian communications is introduced and used in this paper as a prerequisite to real world experiments. Both stationary and moving pedestrians are considered in the model and hardware-in-the-loop simulations. Two real world experiments are also presented to demonstrate the V2P based avoidance of crashes between low speed autonomous shuttles and pedestrians.

Deep reinforcement learning for pedestrian collision avoidance and human-machine cooperative driving

With the development of intelligent driving technology, human-machine cooperative driving is significant to improve driving safety in abnormal situations, such as distraction or incorrect operations of drivers. For human-machine cooperative driving, the capacity of pedestrian collision avoidance is fundamental and important. This paper proposes a novel learning-based human-machine cooperative driving scheme (L-HMC) with active collision avoidance capacity using deep reinforcement learning. Firstly, an improved deep Q-network (DQN) method is designed to learn the optimal driving policy for pedestrian collision avoidance. In the improved DQN method, two replay buffers with nonuniform samples are designed to shorten the learning process of the optimal driving policy. Then, a human-machine cooperative driving scheme is proposed to assist human drivers with the learned driving policy for pedestrian collision avoidance when the driving behavior of human drivers is dangerous to the pedestrian. The effectiveness of the human-machine cooperative driving scheme is verified on the simulation platform PreScan using a real vehicle dynamic model. The results demonstrate that the deep reinforcement learning-based method can learn an effective driving policy for pedestrian collision avoidance with a fast convergence rate. Meanwhile, the proposed human-machine cooperative driving scheme L-HMC can avoid potential pedestrian collisions through flexible policies in typical scenarios, therefore improving driving safety.