Real-time Collision Avoidance for Pedestrian and Bicyclist Simulation: A Smooth and Predictive Approach

A formulation that makes possible the integration of collision prediction and avoidance stages for mobile robots moving in general terrains containing moving obstacles is presented. A dynamic model of the mobile robot and the dynamic constraints are derived. Collision avoidance is guaranteed if the distance between the robot and a moving obstacle is nonzero. A nominal trajectory is assumed to be known from off-line planning. The main idea is to change the velocity along the nominal trajectory so that collisions are avoided. A feedback control is developed and local asymptotic stability is proved if the velocity of the moving obstacle is bounded. Simulation results verify the value of the proposed strategy. >

An integrated collision prediction and avoidance scheme for mobile robots in non-stationary environments

This paper presents a new design for formation control on a group of autonomous humanoid robots with obstacle and collision avoidance ability that inspired by human walking behavior in a pedestrian crowd. This human walking behavior model is known as Social Force Model (SFM) and has been widely used to predict individual movement in a crowd in many variety of situation. We combine consensus algorithm with virtual structure approach for formation control and SFM for obstacle and collision avoidance. In this research, we induced some factors in SFM into consensus equation and then implemented into a group of humanoid robots. The aim of the integration is to create a group of robots that are capable of carrying out its collective tasks while still able to maintain its safety. The use of perception effect, distinct obstacle and collision avoidance function on the algorithm will differentiate algorithm with the others. The attractive feature of this new design is the various behaviors of robots to go back to their initial formation after they avoid obstacles. In the case of robot is trapped in a crowded situation (singularity condition), robot will still trying to look a new position, until it find a condition that allow him to move forward. We verify the proposed algorithm by some simulations and experiments.

Ensuring safety at intersections is a significant challenge, highlighting the urgent need for robust collision prevention systems. This study proposed an innovative Collision Warning (CW) system designed to proactively detect and warn of potential collisions between different traffic participants at urban intersections. The system seamlessly integrates real-time video surveillance, YOLOv3-based object detection, and sophisticated data processing technology to accurately identify collision risks and issue alerts in a timely manner. The system was validated using MATLAB and Unreal Engine for a variety of scenarios including vehicles, pedestrians, and cyclists, considering reaction times, communication delays, and braking distances, and ultimately proved to be capable of accurately identifying potential collision risks, even in complex scenarios with multiple interacting objects. The system output displays target locations and collision predictions, allowing operators to quickly perform evasive maneuvers to prevent potential collisions. The test results show that the system can correctly output warning information in all the test scenarios in the virtual environment, the system positioning error is less than 1m, and the reaction time reserved for the driver is more than 1.42s. This solution offers significant advantages over other CW systems in terms of flexibility, cost-effectiveness, and privacy protection.

Incorporating decision-making capability as an intelligence aspect into crowd dynamics models is crucial factor for reproducing realistic pedestrian flow. Crowd dynamics models are still suffering from poor representation of essential behaviors such as lane changing behavior. In this article, we provide the simulated pedestrians in the social force model more intelligence as an extension to the pedestrian’s investigation capability in bidirectional walkways, to let the model appear more representative of what actually happens in reality. In the proposed model, the lane’s structure is modeled as social network. Thereby, the simulated pedestrians with inconvenient walking can detect the available lanes inside his environment, investigate their attractions, and then make decisions to join the most attractive one. Simulations are performed to validate the work qualitatively by tracing the behavior of the simulated pedestrians and studying the impact of this behavior on lane formation. Finally, a quantitative measurement is used to study the effect of our contribution on the pedestrians’ efficiency of motion.

Pedestrian movement simulation models are used in various areas, such as building evacuation, transportation engineering, and safety management of large events. It also provides effective means to uncover underlying mechanisms of collective behaviors. In this work, a modified heuristics-based model is presented. In this model, the potential collisions in the moving process are explicitly considered. Meanwhile, a series of simulations is conducted in two typical scenarios to demonstrate the influence of critical parameters on model performance. It is found that when facing a wide obstacle in a corridor, the larger the visual radius, the earlier the pedestrian starts to make a detour. In addition, when a pedestrian observes a large crowd walking toward him, he chooses to make a detour and moves in the flow in a uniform direction. Furthermore, the model can reproduce the lane formation pedestrian flow phenomena in relatively high-density situations. With the increase of pedestrian visual radius and the weight of potential collision resistance, more stable pedestrian lanes and fewer moving-through-the-counterflow pedestrians can be observed. In terms of model validation, the density-speed relationship of simulation results accords well with that of the published empirical data. Our results demonstrate that the modified heuristics-based model can overcome the deficiency of the original model, and reproduce more realistic pedestrian movement behavior.

The increasing number of vehicles in modern cities brings the problem of increasing crashes. One of the applications or services of Intelligent Transportation Systems (ITS) conceived to improve safety and reduce congestion is collision avoidance. This safety critical application requires sub-meter level vehicle state estimation accuracy with very high integrity, continuity and availability, to detect an impending collision and issue a warning or intervene in the case that the warning is not heeded. Because of the challenging city environment, to date there is no approved method capable of delivering this high level of performance in vehicle state estimation. In particular, the current Global Navigation Satellite System (GNSS) based collision avoidance systems have the major limitation that the real-time accuracy of dynamic state estimation deteriorates during abrupt acceleration and deceleration situations, compromising the integrity of collision avoidance. Therefore, to provide the Required Navigation Performance (RNP) for collision avoidance, this paper proposes a novel Particle Filter (PF) based model for the integration or fusion of real-time kinematic (RTK) GNSS position solutions with electronic compass and road segment data used in conjunction with an Autoregressive (AR) motion model. The real-time vehicle state estimates are used together with distance based collision avoidance algorithms to predict potential collisions. The algorithms are tested by simulation and in the field representing a low density urban environment. The results show that the proposed algorithm meets the horizontal positioning accuracy requirement for collision avoidance and is superior to positioning accuracy of GNSS only, traditional Constant Velocity (CV) and Constant Acceleration (CA) based motion models, with a significant improvement in the prediction accuracy of potential collision.

In the intelligent transportation system, various accident avoidance techniques have been applied. Among them, one of the most common issues is the collision, which is yet unsolved problem. To this end, we develop collision warning and avoidance system (CWAS), which is implemented in the wheeled mobile robot. Likewise, path planning is a crucial problem in the mobile robots to perform a given task correctly. Here, a tracking system is presented for the mobile robot, which follows an object. Thus, we have implemented an integrated CWAS and tracking system in the mobile robot. Both systems can be activated independently. In the CWAS, the robot is controlled through a remotely controlled device, and collision prediction and avoidance functions are performed. In the tracking system, the robot performs tasks autonomously, where the robot maintains a constant distance from the followed object. The surrounding information is obtained through the range sensors, and the control functions are performed through the microcontroller. The front, left, and right sensors are activated to track the object, and all the sensors are used for the CWAS. Two algorithms based on the sensory information are developed with the distance control approach. The proposed system is tested using the binary logic controller and the fuzzy logic controller (FLC). The comparison of both controllers is also described by preferring time delay and complexity. The efficiency of the robot is improved by increasing smoothness in motion using the FLC, achieving accuracy in tracking, and advancements in the CWAS. Finally, simulation and experimental outcomes have displayed the authenticity of the system.

Pedestrian movement simulation for an airport considering social distancing strategy

Local collision avoidance algorithms in crowd simulation often ignore agents beyond a neighborhood of a certain size. This cutoff can result in sharp changes in trajectory when large groups of agents enter or exit these neighborhoods. In this work, we exploit the insight that exact collision avoidance is not necessary between agents at such large distances, and propose a novel algorithm for extending existing collision avoidance algorithms to perform approximate, long-range collision avoidance. Our formulation performs long-range collision avoidance for distant agent groups to efficiently compute trajectories that are smoother than those obtained with state-of-the-art techniques and at faster rates. Comparison to real-world data demonstrates that crowds simulated with our algorithm exhibit an improved speed sensitivity to density similar to human crowds. Another issue often sidestepped in existing work is that discrete and continuum collision avoidance algorithms have different regions of applicability. For example, low-density crowds cannot be modeled as a continuum, while high-density crowds can be expensive to model using discrete methods. We formulate a hybrid technique for crowd simulation which can accurately and efficiently simulate crowds at any density with seamless transitions between continuum and discrete representations. Our approach blends results from continuum and discrete algorithms, based on local density and velocity variance. In addition to being robust across a variety of group scenarios, it is also highly efficient, running at interactive rates for thousands of agents on portable systems.

Pedestrian choice behavior analysis and simulation of ticket gate machine in rail transit station

Ship maneuvering toward a dock is a hot research topic in the field of autonomous ships. How to realize autonomous low-speed maneuver to a designated location under environmental disturbances is the fundamental problem at present. In addition, potential collisions with other nearby vessels and evasive maneuvers that meet maritime regulations increase the complexity of maneuvering. This paper presents an effective ship control strategy for collision-free maneuver toward a dock. In the strategy, a line-of-sight (LOS) algorithm is utilized to steer the ship along a pre-planned path toward the dock. A collision risk factor that takes ship's maneuvering characteristics, ship domain and relative velocity into account is designed for collision avoidance. Evasive maneuvers complying with the main rules of the international collision avoidance regulations at sea can be achieved based on the risk factor. A ship bumper is constructed, based on which the strategy can switch to either “path following” or “collision avoidance”. Numerical simulations for different encounter situations including head-on, starboard-crossing and overtaking under wind perturbations are carried out. The results show the proposed strategy is able to keep the ship domain free during maneuvering and steer the ship to the docking area in a safe and appropriate manner.

Modified social force model considering emotional contagion for crowd evacuation simulation

Modeling pedestrian–vehicle interaction behaviors not only helps better predict the intentions and actions of traffic participants but also contributes to generating more realistic pedestrian trajectories for testing autonomous vehicles. Most existing pedestrian–vehicle interaction models use repulsive forces toward target directions to avoid collisions. However, pedestrian agents in these models lack the ability to plan avoidance routes based on their positions when facing conflicting vehicles, leading to poor simulation effects at unsignalized intersections. By analyzing the crossing trajectories of pedestrians at unsignalized intersections through video data, we observed that when participants reject a current vehicle gap, they may tend to move toward the vehicle’s rear to start crossing the traffic flow earlier, thereby obtaining a safer opportunity to cross the road. In contrast, most previous pedestrian–vehicle interaction models only simulated pedestrians’ avoidance by moving away from vehicles. In response, we propose a pedestrian–vehicle interaction model incorporating pedestrian avoidance tendencies, which is based on the social force framework. Our improvements include refining the vehicle’s influence on pedestrians in lateral and longitudinal dimensions. The pedestrian agents in this model can make appropriate crossing decisions and select collision avoidance paths according to traffic conditions. This model can simulate pedestrian–vehicle interaction scenarios at unsignalized intersections and can be extended to pedestrian safety testing for autonomous vehicles.

A probabilistic approach for collision avoidance of uncertain moving objects within black zones