Avoidance Maneuvers Research Articles

Measurement and modelling of driver learning of steering control during successive obstacle avoidance manoeuvres

Understanding of driver behaviour can provide invaluable insight for the design of vehicles and driver assistance systems. Most existing human driver models do not incorporate driver learning or the effect of a driver's confidence in their predictions of future states, both of which affect human-generated control actions. In this paper, human driver steering control is assessed based on experimental data, then a driver model is proposed which captures driver learning and is capable of reproducing a wide range of human control styles by the selection of appropriate parameters. The driver model learns an internal model of the vehicle dynamics from experience, using a Gaussian Process, then selects control actions via Model Predictive Control. The results verify the model's capacity to capture the learning drivers achieve over time and to replicate various observed cautious and adventurous behaviours.

Optimizing Consider-Covariance Models for Realistic Orbit Errors and Application to Collision Avoidance

Precise knowledge about the orbit state vectors and the associated uncertainties are crucial for reliable conjunction assessment and efficient mitigation of on-orbit collision risks through collision avoidance maneuvers by active satellites. The decision-making process heavily relies on the orbit accuracy and the uncertainty realism of the encountering objects, primarily space debris, and the maneuvering satellite itself. The process of determining an orbit creates an estimate of the orbit state and its associated state covariance matrix. This estimate serves as the initial value for predicting the orbit’s uncertainty at the time of closest approach. To determine and numerically propagate realistic orbit errors, the uncertainties of the dynamic model must be taken into account. One method that fulfils this purpose is consider covariance propagation, provided that suitable consider parameters and their variances have been established. This paper presents a novel method for optimizing the consider covariance parameters from past mission data. Real orbit data from multiple low Earth orbit satellites controlled by the DLR, German Aerospace Center’s German Space Operations Center are used to calibrate and evaluate different error models, including covariance parameters and other error terms. The results demonstrate improved uncertainty realism in orbit predictions and subsequent benefits for collision avoidance. Finally, this paper presents the required steps for integrating the new method into the existing collision avoidance system, along with initial results from conjunction assessment.

Research on Course-Changing Performance of a Large Ship with Spoiler Fins

The poor maneuverability inherent to large ships is a non-negligible problem that restricts the development of the shipping industry, as large ships can only cruise at an excessively conservative speed when they encounter complicated traffic conditions; nevertheless, ship collision accidents still occasionally occur. In the present study, the novel concept of spoiler fins for modern large ships is proposed. In order to assess their effectiveness in enhancing ship maneuverability, a KRISO container ship (KCS) was selected to carry a pair of spoiler fins, after which a simplified simulation approach for saving the calculation resource was designed for ship collision avoidance conditions, and a full-scale numerical model, including the ship hull, fin, and fluid field domain, was established. Transient-state hydrodynamic forces were calculated during collision avoidance maneuvers using the CFD method; the pressure and velocity contours around the ship were demonstrated; and the ship motion trajectories under different initial ship speeds were simulated and predicted through the adoption of overset mesh and 6-DOF dynamic mesh techniques. Eventually, the improved course-changing performance, dependent on the spoiler fins, was validated.

Graph-driven multi-vessel long-term trajectories prediction for route planning under complex waters

Current collision avoidance algorithms used in autonomous navigation vessels are hindered by limited long-term visibility of dynamic obstacles, resulting in overly cautious and frequent avoidance maneuvers that can actually increase the risk of collisions in complex waterways. Therefore, this paper proposed a novel graph-driven multi-vessel long-term trajectory prediction method (termed GMLTP), which extends the length of real-time and accurate prediction of other vessel trajectories. GMLTP can enhance collision avoidance algorithms by enabling more anticipatory trajectory prediction, ultimately supporting real-time route planning in creating safer, more efficient, and optimized routes. Specifically, GMLTP consists of a multi-graph spatial convolution (MGSC) layer and a probability sparse (ProbSparse) self-attention Transformer. MGSC is a finer spatial interactions extractor, which supports the modeling of spatial dependency evolution on longer sequences and thus improves the perception of long-term trends, while ProbSparse self-attention Transformer is used to reduce the computation of learning long-term global time dependencies and thus extending the predictable length. Extensive experimental results indicate that GMLTP exhibits better accuracy and generalization in prediction tasks beyond 48-timesteps (each time step is 10 s), which can provide better assistance to current real-time route planning tasks.

Enhancing navigation and obstacle avoidance with a vibrotactile device as secondary electronic travel aid

People with visual impairments commonly rely on the use of a white cane to navigate and avoid obstacles. Although this analog tool is highly reliable and easy to use, its drawback is the impossibility to anticipate obstacles beyond reach and routes, as well as obstacles above waist level. Electronic travel aids (ETAs) and sensory substitution devices (SSDs) are new technological solutions designed to enhance the tactile and/or auditory capabilities to access the information needed to overcome those drawbacks. In the present study, 25 individuals with visual impairments used the T-Sight, a vibrotactile SSD, and/or the white cane in a navigation task involving obstacle avoidance. While the performance achieved with the device, measured by the number of collisions and walking speed, did not surpass the white cane, the SSD did have a positive impact on ambulation. Participants reduced the number of white cane touches towards environmental obstacles and performed obstacle avoidance maneuvers earlier. These results demonstrate the potential of vibrotactile devices to address the limitations of the white cane.

Intention inference for space targets using deep convolutional neural network

Intention inference for space targets is crucial for space situational awareness. This paper introduces a rapid and precise method for recognizing the intentions of non-cooperative space targets using a deep convolutional neural network (CNN). By employing a relative orbital dynamics model, an analysis of relative motion was performed, resulting in the identification of 11 distinct motion intentions for space targets. This study also describes how to generate relative motion trajectory images to create a training set for intention inference, effectively converting the problem into one of image recognition and classification. Extensive simulations were carried out to fine-tune the network hyperparameters, and the results highlight the exceptional performance of the proposed CNN-based method, which achieved an accuracy of 99.682%. This method significantly enhances recognition accuracy over other neural network-based methods for space objects and offers considerable potential for applications like spacecraft collision avoidance and strategic maneuvers among space targets.

Discomfort in pedestrian-electric scooter interactions during frontal approaches

BackgroundAs urban landscapes rapidly integrate e-scooters into their transportation ecosystems, understanding pedestrian-e-scooter interactions becomes paramount for safety and planning. This study investigates pedestrian discomfort levels and avoidance strategies when encountering an e-scooter approaching from the front. Methods25 participants were exposed to e-scooters approaching at three different speeds and lateral distances. Avoidance paths were plotted, and subjective discomfort levels were recorded and analysed. ResultsOur findings underscored two key behaviours: 1) As the speed of the e-scooter increased, participants initiated avoidance manoeuvres from a further distance ahead, suggesting a heightened perception of risk. 2) Regardless of the e-scooter's speed, the lateral distance maintained during passing remained fairly constant. However, when the e-scooter's initial lateral position was closer to participants, both the initiation distance for avoidance and the reported discomfort level increased noticeably. ConclusionThe findings underscore the critical influence of lateral distance and e-scooter speed on pedestrian comfort and avoidance behaviour. These insights can guide urban planners and policymakers in designing safer and more efficient shared spaces.

Establishing requirements for lunar and cislunar orbital debris tracking

There is a need to formally coordinate lunar and cislunar space traffic management to mitigate the risk of collisions with micrometeoroids and orbital debris in this space domain. To control this hazard, it will be critical to develop a high-fidelity orbital debris catalog. This catalog will be maintained by monitoring and propagating the trajectory of objects. The need to perform a debris avoidance maneuver for collision avoidance will depend on the fidelity of the propagated debris trajectory. A larger uncertainty (magnitude as a function of time) will require a larger maneuver and a higher likelihood of the need to perform this maneuver. This study assesses debris avoidance maneuvers and corresponding corrective actions to recover the desired mission trajectory as a way to evaluate the desired capability of tracking of objects in lunar and cislunar orbit. The baseline Earth-to-Moon trajectory was that of the Artemis I mission. Typical conjunction assessments were postulated at 100,000 km from Earth's center (approximately a quarter of the way to the moon) and at lunar orbit insertion (LOI). For these two cases, the required debris avoidance maneuver (and hence impact to the mission) is tied to the uncertainty in orbital debris tracking. The study provides a methodology and baseline inputs to establish future requirements of debris tracking in lunar and cislunar orbits. It also reinforces the importance of long-term sustainability for lunar missions, specifically preventing the generation of orbital debris.

Long-Term Fuel-Optimal Collision Avoidance Maneuvers with Station-Keeping Constraints

This work presents a sequential convex program method to compute fuel-optimal collision avoidance maneuvers for long-term encounters. The low-thrust acceleration model is used to account for the control, but the method can compute high-thrust maneuvers by increasing the maximum available acceleration. Dealing with the long-term conjunction poses additional challenges compared to the short-term problem because the encounter is not instantaneous. Thus, under the assumption of Gaussian statistics, the probability of collision is replaced by a simpler metric, the instantaneous probability of collision (IPoC), and a keep-out zone constraint is formulated as a continuous condition to be respected throughout the time frame of interest. The robustness of the solution is improved by introducing a constraint on the sensitivity of IPoC. Furthermore, the collision avoidance problem is coupled with the classical station-keeping requirement for geostationary Earth orbit satellites and with a return to the nominal orbit condition for low Earth orbit satellites. Even though no guarantee is given for the recovery of the global optimum solution, numerical simulations in different orbital regimes show that the proposed approach can yield a local fuel-optimal solution with a run time suitable for autonomous applications.

Drag augmentation for collision avoidance in LEO

Space debris proliferation in Low Earth Orbit (LEO) has heightened the urgency for effective Collision Avoidance Manoeuvres (CAMs). This work presents a pioneering framework aimed at devising a novel collision avoidance manoeuvre design for drag-augmentation small platforms. The framework facilitates the alteration of drag acceleration by adjusting the satellite’s ballistic coefficient through cross-sectional area changes. This approach generates controlled deviations in the nominal trajectory, offering a feasible solution for collision avoidance without necessitating thrusters or fuel consumption.The paper introduces an analytical method for propagating drag augmentation manoeuvres and applies it for collision avoidance studies purposes. The formulation followed to implement this manoeuvre within a numerical propagator is presented, as well as the optimisation process developed for the application of drag augmentation manoeuvres in collision avoidance scenarios. Real-world applications showcase the suitability of these approaches, confirming the use of drag augmentation manoeuvres to avoid collisions in LEO. Additionally, the requirements and boundaries of the strategy, including altitude restrictions and satellite-specific properties, are discussed.

Influences of Space Weather Forecasting Uncertainty on Satellite Conjunction Assessment

AbstractA significant increase in the number of anthropogenic objects in Earth orbit has necessitated the development of satellite conjunction assessment and collision avoidance capabilities for new spacecraft. Neutral mass density variability in the thermosphere, driven by enhanced geomagnetic activity and solar EUV absorption, is a major source of satellite propagation error. This work investigates the impacts of space weather driver forecasting uncertainty on satellite drag and collision avoidance maneuver decision‐making. Since most operational space weather driver forecasts do not offer an uncertainty assessment, the satellite operator community is left to make dangerous assumptions about the trustworthiness of the forecast models they use to perform satellite state propagation. Climatological persistence‐based forecast models are developed for F10.7 and Kp. These models accurately capture the heteroscedastic and, at times, highly non‐Gaussian uncertainty distribution on forecasts of the drivers of interest. A set of realistic satellite conjunction scenarios is simulated to demonstrate the contributions of space weather driver forecast uncertainty on the probability of collision and maneuver decisions. Improved driver forecasts, especially forecasts of F10.7, are demonstrated to be very useful for enabling durable maneuver decisions with additional lead time (up to 24 hr for the period examined), though the improvement depends on the specific conjunction scenario of interest.

Obstacle encounter probability dependent local path planner for UAV operation in urban environments

Unmanned aerial vehicles (UAVs) are well-suited for various short-distance missions in urban environments. However, the path planner of such UAV is constantly challenged with the choice between avoiding obstacles horizontally or vertically. If the path planner relies on sensor information only, i.e. the path planner is a local planner, usually predefined manoeuvres or preferences are used to find a possible way. However, this method is stiff and inflexible. This work proposes a probabilistic decision-maker to set the control parameters of a classic local path planner during a flight mission. The decision-maker defines whether performing horizontal or vertical avoidance is preferable based on the probability of encountering a given number of obstacles. Here, the decision-maker considers predictions of possible future avoidance manoeuvres. It also defines an ideal flight altitude based on the probability of encountering obstacles. This work analyses the building height of all European capital cities and the probability of encountering obstacles at different altitudes to feed the decision-maker. We tested the feasibility of the proposed decision-maker with the 3DVFH*, a commonly used local path planner, in multiple simulations. The proposed probabilistic decision-maker allows the local path planner to reach the goal point significantly more often than the standard version of the 3DVFH*.

Trajectory Planning and Tracking Using Decoupled CBF-QPs for Safe Navigation of Quadrotors

Abstract Control barrier function-based quadratic program (CBF-QP) provides an avenue for agile and numerically efficient obstacle avoidance algorithms. However, the CBF-QP methods may lead to lengthy detours and undesirable avoidance maneuvers. This paper proposes a bi-level CBF-QP for the safe navigation of quadrotors. A Planning-QP is proposed to create a safe reference trajectory that shadows the actual reference trajectory with prescribed avoidance acceleration, velocity, distance, and direction during the avoidance maneuver. A control Lyapunov function (CLF) ensures that modified reference closely matches the actual reference outside the avoidance regions and multiple control barrier functions (CBFs) ensure the safety and smoothness of the avoidance trajectory. Model uncertainties can undermine the safety of the quadrotor while tracking the modified reference. Hence, a Tracking-QP is designed to achieve accurate tracking with ensured safe maneuvering around obstacles, where a new CBF is constructed to prevent actuator saturation. Prescribed attitude bounds are ensured via additional acceleration constraints in the Tracking-QP. The proposed method is validated using numerous experiments involving various static obstacles where the quadrotor carries different payloads.

Determination of Ship Collision Avoidance Timing Using Machine Learning Method

The accurate timing for collision avoidance actions is crucial for preventing maritime collisions. Traditional methods often rely on collision risk assessments, using quantitative indicators like the Distance to the Closest Point of Approach (DCPA) and the Time to the Closest Point of Approach (TCPA). Ship Officers on Watch (OOWs) are required to execute avoidance maneuvers once these indicators reach or exceed preset safety thresholds. However, the effectiveness of these indicators is limited by uncertainties in the maritime environment and the human behaviors of OOWs. To address these limitations, this study introduces a machine learning method to learn collision avoidance behavior from empirical data of ship collision avoidance, particularly in cross-encounter situations. The research utilizes Automatic Identification System (AIS) data from the open waters around Ningbo Zhoushan Port. After data preprocessing and applying spatio-temporal constraints, this study identifies ship trajectory pairs in crossing scenarios and calculates their relative motion parameters. The Douglas–Peucker algorithm is used to identify the timing of ship collision avoidance actions and a collision avoidance decision dataset is constructed. The Random Forest algorithm was then used to analyze the factors affecting the timing of collision avoidance, and six key factors were identified: the distance, relative speed, relative bearing, DCPA, TCPA, and the ratio of the lengths of the giving-way and stand-on ships. These factors serve as inputs for the XGBoost algorithm model, which is enhanced with Particle Swarm Optimization (PSO), and thus constructing a ship collision avoidance decision model. In addition, considering the inherent errors in any model and the dynamic nature of the ship collision avoidance process, an action time window for collision avoidance is introduced, which provides a more flexible time range for ships to make timely collision avoidance responses based on actual conditions and the specific encounter environment. This model provides OOWs with accurate timing for taking collision avoidance decisions. Case studies have validated the practicality and effectiveness of this model, offering new theoretical foundations and practical guidance for maritime collision avoidance.

Analysis of the neural network application effectiveness in predicting collision avoidance maneuvers for two vessels

Analysis of the neural network application effectiveness in predicting collision avoidance maneuvers for two vessels

Improving local path planning for UAV flight in challenging environments by refining cost function weights

Unmanned Aerial Vehicles (UAV) constantly gain in versatility. However, more reliable path planning algorithms are required until full autonomous UAV operation is possible. This work investigates the algorithm 3DVFH* and analyses its dependency on its cost function weights in 2400 environments. The analysis shows that the 3DVFH* can find a suitable path in every environment. However, a particular type of environment requires a specific choice of cost function weights. For minimal failure, probability interdependencies between the weights of the cost function have to be considered. This dependency reduces the number of control parameters and simplifies the usage of the 3DVFH*. Weights for costs associated with vertical evasion (pitch cost) and vicinity to obstacles (obstacle cost) have the highest influence on the failure probability of the local path planner. Environments with mainly very tall buildings (like large American city centres) require a preference for horizontal avoidance manoeuvres (achieved with high pitch cost weights). In contrast, environments with medium-to-low buildings (like European city centres) benefit from vertical avoidance manoeuvres (achieved with low pitch cost weights). The cost of the vicinity to obstacles also plays an essential role and must be chosen adequately for the environment. Choosing these two weights ideal is sufficient to reduce the failure probability below 10%.

From Perception to Prediction: Leveraging Explainable AI in Self-Driving Cars for Enhanced Passenger Trust

Self-driving cars hold immense potential for revolutionizing transportation. However, public acceptance hinges on trust in the car's ability to navigate safely and make critical decisions. This trust deficit stems from the "black box" nature of traditional machine learning models used in self-driving cars. Passengers are left in the dark about the car's perception of the environment and the reasoning behind its actions. This research proposes leveraging Explainable Artificial Intelligence (XAI) techniques to enhance passenger trust in self-driving cars. By incorporating explainability into the perception and prediction modules of the car's decision- making system, we aim to provide passengers with real-time insights into how the car perceives its surroundings and translates those perceptions into driving decisions. This paper explores various XAI methods suitable for self-driving car applications. We discuss the integration of these techniques into the perception and prediction pipelines, enabling the car to explain its reasoning behind lane changes, obstacle avoidance maneuvers, and other critical actions. We evaluate the effectiveness of the proposed approach through user studies, assessing how explainability can improve passenger trust and comfort in self-driving vehicles. The ultimate goal of this research is to foster greater transparency and trust in self-driving car technology, paving the way for wider public adoption and a future of safe and reliable autonomous transportation.

Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety

The application of autonomous driving system (ADS) technology can significantly reduce potential accidents involving vulnerable road users (VRUs) due to driver error. This paper proposes a novel hierarchical deep reinforcement learning (DRL) framework for high-performance collision avoidance, which enables the automated driving agent to perform collision avoidance maneuvers while maintaining appropriate speeds and acceptable social distancing. The novelty of the DRL method proposed here is its ability to accommodate dynamic obstacle avoidance, which is necessary as pedestrians are moving dynamically in their interactions with nearby ADSs. This is an improvement over existing DRL frameworks that have only been developed and demonstrated for stationary obstacle avoidance problems. The hybrid A* path searching algorithm is first applied to calculate a pre-defined path marked by waypoints, and a low-level path-following controller is used under cases where no VRUs are detected. Upon detection of any VRUs, however, a high-level DRL collision avoidance controller is activated to prompt the vehicle to either decelerate or change its trajectory to prevent potential collisions. The CARLA simulator is used to train the proposed DRL collision avoidance controller, and virtual raw sensor data are utilized to enhance the realism of the simulations. The model-in-the-loop (MIL) methodology is utilized to assess the efficacy of the proposed DRL ADS routine. In comparison to the traditional DRL end-to-end approach, which combines high-level decision making with low-level control, the proposed hierarchical DRL agents demonstrate superior performance.

A Dynamic Programming Approach to the Collision Avoidance of Autonomous Ships

The advancement of autonomous capabilities in maritime navigation has gained significant attention, with a trajectory moving from decision support systems to full autonomy. This push towards autonomy has led to extensive research focusing on collision avoidance, a critical aspect of safe navigation. Among the various possible approaches, dynamic programming is a promising tool for optimizing collision avoidance maneuvers. This paper presents a DP formulation for the collision avoidance of autonomous vessels. We set up the problem framework, formulate it as a multi-stage decision process, define cost functions and constraints focusing on the actual requirements a marine maneuver must comply with, and propose a solution algorithm leveraging parallel computing. Additionally, we present a greedy approximation to reduce algorithm complexity. We put the proposed algorithms to the test in realistic navigation scenarios and also develop an extensive test on a large set of randomly generated scenarios, comparing them with the RRT* algorithm using performance metrics proposed in the literature. The results show the potential benefits of an autonomous navigation or decision support framework.

Implementation of MIMO Radar-Based Point Cloud Images for Environmental Recognition of Unmanned Vehicles and Its Application

High-performance radar systems are becoming increasingly popular for accurately detecting obstacles in front of unmanned vehicles in fog, snow, rain, night and other scenarios. The use of these systems is gradually expanding, such as indicating empty space and environment detection rather than just detecting and tracking the moving targets. In this paper, based on our high-resolution radar system, a three-dimensional point cloud image algorithm is developed and implemented. An axis translation and compensation algorithm is applied to minimize the point spreading caused by the different mounting positions and the alignment error of the Global Navigation Satellite System (GNSS) and radar. After applying the algorithm, a point cloud image for a corner reflector target and a parked vehicle is created to directly compare the improved results. A recently developed radar system is mounted on the vehicle and it collects data through actual road driving. Based on this, a three-dimensional point cloud image including an axis translation and compensation algorithm is created. As a results, not only the curbstones of the road but also street trees and walls are well represented. In addition, this point cloud image is made to overlap and align with an open source web browser (QtWeb)-based navigation map image to implement the imaging algorithm and thus determine the location of the vehicle. This application algorithm can be very useful for positioning unmanned vehicles in urban area where GNSS signals cannot be received due to a large number of buildings. Furthermore, sensor fusion, in which a three-dimensional point cloud radar image appears on the camera image, is also implemented. The position alignment of the sensors is realized through intrinsic and extrinsic parameter optimization. This high-performance radar application algorithm is expected to work well for unmanned ground or aerial vehicle route planning and avoidance maneuvers in emergencies regardless of weather conditions, as it can obtain detailed information on space and obstacles not only in the front but also around them.