Off-road Scenarios Research Articles

Multibody Dynamics and Terramechanics-based modeling and simulation of Quarter-Car with Suspension

Abstract While tires only compress when acted upon by a load in on-road scenarios, in off-road conditions, on the other hand, the tires not only undergo compression but also sinkage into the ground, in a manner that depends on the terrain. The tire-ground contact, in turn, affects the forces acting on the suspension system. Hence, it is necessary to study the vertical dynamic response of a system in off-road conditions by accounting for the terramechanics phenomenon (tire-terrain interface). The forces acting at the tire and terrain interface in off-road conditions have been studied in terramechanics separately; however, their integration with multibody systems is relatively less explored. In this paper, a multibody dynamic-based modeling and simulation of a quarter car with a linear spring-damper suspension system for off-road vehicles is presented. The generalized external forces are obtained using the Bekker-Wong based soil pressure-sinkage approach for two different kind of multibody systems interacting with sandy loam terrain. This model is integrated with the Tangent Space Ordinary Differential Equations of the quarter car and suspension system and solved using numerical integration techniques. Thus, by accounting for the terramechanics in the multibody system, the technique provides a more realistic response of the system in off-road scenarios.

Real-time path planning for autonomous vehicle off-road driving.

Autonomous driving is a growing research area that brings benefits in science, economy, and society. Although there are several studies in this area, currently there is no a fully autonomous vehicle, particularly, for off-road navigation. Autonomous vehicle (AV) navigation is a complex process based on application of multiple technologies and algorithms for data acquisition, management and understanding. Particularly, a self-driving assistance system supports key functionalities such as sensing and terrain perception, real time vehicle mapping and localization, path prediction and actuation, communication and safety measures, among others. In this work, an original approach for vehicle autonomous driving in off-road environments that combines semantic segmentation of video frames and subsequent real-time route planning is proposed. To check the relevance of the proposal, a modular framework for assistive driving in off-road scenarios oriented to resource-constrained devices has been designed. In the scene perception module, a deep neural network is used to segment Red-Green-Blue (RGB) images obtained from camera. The second traversability module fuses Light Detection And Ranging (LiDAR) point clouds with the results of segmentation to create a binary occupancy grid map to provide scene understanding during autonomous navigation. Finally, the last module, based on the Rapidly-exploring Random Tree (RRT) algorithm, predicts a path. The Freiburg Forest Dataset (FFD) and RELLIS-3D dataset were used to assess the performance of the proposed approach. The theoretical contributions of this article consist of the original approach for image semantic segmentation fitted to off-road driving scenarios, as well as adapting the shortest route searching A* and RRT algorithms to AV path planning. The reported results are very promising and show several advantages compared to previously reported solutions. The segmentation precision achieves 85.9% for FFD and 79.5% for RELLIS-3D including the most frequent semantic classes. While compared to other approaches, the proposed approach is faster regarding computational time for path planning.

Co-optimization of Power Allocation and Speed Trajectory for Autonomous HEVs in Off-Road Scenarios Considering Vehicle Dynamics

Co-optimization of Power Allocation and Speed Trajectory for Autonomous HEVs in Off-Road Scenarios Considering Vehicle Dynamics

OffRoadSynth Open Dataset for Semantic Segmentation using Synthetic-Data-Based Weight Initialization for Autonomous UGV in Off-Road Environments

This article concerns the issue of image semantic segmentation for the machine vision system of an autonomous Unmanned Ground Vehicle (UGV) moving in an off-road environment. Determining the meaning (semantics) of the areas visible in the recorded image provides a complete understanding of the scene surrounding the autonomous vehicle. It is crucial for the correct determination of a passable route. Nowadays, semantic segmentation is generally solved using convolutional neural networks (CNN), which can take an image as input and output the segmented image. However, proper training of the neural network requires the use of large amounts of data, which becomes problematic in the situation of low availability of large, dedicated image data sets that consider various off-road situations - driving on various types of roads, surrounded by diverse vegetation and in various weather and light conditions. This study introduces a synthetic image dataset called “OffRoadSynth” to address the training data scarcity for off-road scenarios. It has been shown that pre-training the neural network on this synthetic dataset improves image segmentation accuracy compared to other methods, such as random network weight initialization or using larger, generic datasets. Results suggest that using a smaller but domain-dedicated set of synthetic images to initialize network weights for training on the target real-world dataset may be an effective approach to improving semantic segmentation results of images, including those from off-road environments.

Perception and Planning of Intelligent Vehicles Based on BEV in Extreme Off-Road Scenarios

Perception and Planning of Intelligent Vehicles Based on BEV in Extreme Off-Road Scenarios

Bi-Level Optimization of Speed Trajectory and Power Management for Autonomous HEVs in Off-Road Scenarios

Bi-Level Optimization of Speed Trajectory and Power Management for Autonomous HEVs in Off-Road Scenarios

Secure Proxy Re-Encryption Protocol for FANETs Resistant to Chosen-Ciphertext Attacks

In emergency situations, ensuring the secure transmission of medical information is critical. While existing schemes address on-road emergencies, off-road scenarios present unique challenges due to hazardous locations inaccessible to conventional vehicles. This research introduces a protocol for off-road emergencies, leveraging flying ad hoc networks (FANETs) formed by drones. The protocol, designed for users receiving emergency treatment, employs cryptographic techniques to protect sensitive information. To overcome the challenge of decrypting user medical records at emergency centers without the healthcare provider’s key, proxy re-encryption is employed. The control center (CC) securely generates encryption and decryption keys, facilitating the re-encryption process by the cloud server (CS) and transmission to the emergency center (E). The proposed protocol, free from pairing functions, underwent security and efficiency analyses, demonstrating resilience against chosen-ciphertext attacks (CCA) and collusion resistance (CR). Execution times of approximately 0.02 and 0.0 s for re-encryption and decryption processes, respectively, for a message size of 2000 bytes highlighted the efficiency of the protocol. The research contributes a secure and efficient proxy re-encryption protocol for off-road emergency medical information transmission within FANETs.

On the Avant-Garde IDeS Method for the Future of Car Design Applied to an SUV Project

This case study aims to develop a new innovative SUV (Sport Utility Vehicle) model exploiting IDeS (Industrial Design Structure), which is an engineering approach conceived to optimize car design projects in the automotive industry like never before. A compact SUV was chosen because it is a type of vehicle that is highly requested by customers, and it is extremely successful in the market due to its versatility. In fact, compact SUVs are mixed vehicles that combine the pragmatism of a car with the typical robustness of an off-road vehicle making them suitable both for urban and off-road scenarios. The following pages will illustrate the steps followed for the realization of the final product using the SDE (Stylistic Design Engineering) method and other various design technologies, such as Quality Function Deployment (QFD), Benchmarking (BM) and Top Flop Analysis (TPA). In the final part of this project, the virtual prototyping of the product is carried out using Additive Manufacturing (AM) with an FDM 3D printer. The combination of these methods forms, to all intents and purposes, the IDeS, a newly developed innovative and cutting-edge discipline capable of schematically guiding the new product development process in companies with unprecedented efficiency.

Off-road testing scenario design and library generation for intelligent vehicles

To realize the widespread application and continuous functional development of intelligent vehicles, test and evaluation of vehicle's functionality and Safety Performance in complex off-road scenarios are fundamental. Since traditional distance-based road tests cannot meet the evolving test requirements, a method to design the function-based off-road testing scenario library for intelligent vehicles(IV) is proposed in this paper. The testing scenario library is defined as a critical set of scenarios that can be used for IV tests. First, for the complex and diverse off-road scenarios, a hierarchical, structural model of the test scenario is built. Then, the critical test scenarios are selected adaptively according to the vehicle model to be tested. Next, those parameters representing the challenging test scenarios are selected. The selected parameters need to fit the natural distribution probability of scenarios. The critical test-scenario library is built combing these parameters with the structural model. Finally, the test scenarios that are most approximate to the natural driving scenario are determined with importance sampling theory. The test-scenario library built with this method can provide more critical test scenarios, and is widely applicable despite different vehicle models. Verified by simulation in the off-road interaction scenarios, test would be accelerated significantly with this method, about 800 times faster than testing in the natural road environment.

Low-latency perception in off-road dynamical low visibility environments

Robust systems are required for autonomous driving on non-uniform terrain commonly found in open-pit mines and developing countries. To help narrow the gap in this kind of application, this work proposes a perception system for autonomous vehicles and advanced driver assistance specialized on unpaved roads and off-road environments capable of navigating through rough terrain without a predefined trail. As part of this system, the Configurable Modular Segmentation Network (CMSNet) framework is proposed facilitating the creation of different architectures arrangements. Some CMSNet configurations were ported and trained to segment obstacles and trafficable ground on a new collection of images from unpaved roads and off-road scenarios containing adverse conditions such as night, rain, and dust. It was also performed: an investigation regarding the feasibility of applying deep learning to detect regions where the vehicle can pass through when there is no clear track boundary; a study of how our proposed segmentation algorithms behave in different severity levels of visibility impairment; and an evaluation of field tests carried out with semantic segmentation architectures conditioned for real-time inference. The new dataset (named Kamino) has almost 12,000 new images collected from an operated vehicle with various sensors, including eight cameras capturing synchronized sequences from different points of view. The Kamino dataset has a high number of labeled pixels compared to similar publicly available collections. It includes images collected from an off-road proving ground exclusively assembled for testing the system that emulates an open-pit mine scenario under different adverse conditions of visibility. To achieve embedded real-time inference and allows field tests, many layers of the CMSNet CNN networks were methodically removed and fused using TensorRT, C++, and CUDA. Empirical experiments on two datasets validated the effectiveness of the proposed system. The proposed solution achieves a mIoU of ∼87% (50.40% higher than the PSPNet and 56.21% than the DeepLabV3) on the Kamino dataset, and ∼81 % on the DepScene dataset, reaching up to 29 FPS on the RTX2060 GPU and almost 100 FPS with the optimized configurations, and low standard deviation values with the DrivePX2 computer platform.

Stabilization of vertical motion of a vehicle on bumpy terrain using deep reinforcement learning*

Stabilizing vertical dynamics for on-road and off-road vehicles is an important research area that has been looked at mostly from the point of view of ride comfort. The advent of autonomous vehicles now shifts the focus more towards developing stabilizing techniques from the point of view of onboard proprioceptive and exteroceptive sensors whose real-time measurements influence the performance of an autonomous vehicle. The current solutions to this problem of managing the vertical oscillations usually limit themselves to the realm of active suspension systems without much consideration to modulating the vehicle velocity, which plays an important role by the virtue of the fact that vertical and longitudinal dynamics of a ground vehicle are coupled. The task of stabilizing vertical oscillations for military ground vehicles becomes even more challenging due lack of structured environments, like city roads or highways, in offroad scenarios. Moreover, changes in structural parameters of the vehicle, such as mass (due to changes in vehicle loading), suspension stiffness and damping values can have significant effect on the controller's performance. This demands the need for developing deep learning based control policies, that can take into account an extremely large number of input features and approximate a near optimal control action. In this work, these problems are addressed by training a deep reinforcement learning agent to minimize the vertical acceleration of a scaled vehicle travelling over bumps by controlling its velocity.

Probabilistic Meta-Conv1D Driving Energy Prediction for Mobile Robots in Unstructured Terrains

Driving energy consumption plays an important role in the navigation of autonomous mobile robots in off-road scenarios. However, the accuracy of the driving energy predictions is often affected by a high degree of uncertainty due to unknown and constantly varying terrain properties, and the complex wheel-terrain interaction in unstructured terrains. In this paper, a probabilistic deep meta-learning approach is proposed to model the existing uncertainty in the driving energy consumption and efficiently adapt the probabilistic predictions based on a small number of local measurements. The method expands upon an existing deterministic deep-meta learning model that, in contrast, only provided single-point energy estimates. The performance of the proposed method is compared against the deterministic approach in a 3D-body dynamic simulator over several typologies of deformable terrains and unstructured geometries. In this way, the benefits of the proposed method are illustrated to enhance the predictions with informative probabilistic considerations, which can be crucial to the safety of mobile robots traversing challenging, unstructured environments.

Constraint Embedding for Vehicle Suspension Dynamics

Abstract The goal of this research is to achieve close to real-time dynamics performance for allowing auto-pilot in-the-loop testing of unmanned ground vehicles (UGV) for urban as well as off-road scenarios. The overall vehicle dynamics performance is governed by the multibody dynamics model for the vehicle, the wheel/terrain interaction dynamics and the onboard control system. The topic of this paper is the development of computationally efficient and accurate dynamics model for ground vehicles with complex suspension dynamics. A challenge is that typical vehicle suspensions involve closed-chain loops which require expensive DAE integration techniques. In this paper, we illustrate the use the alternative constraint embedding technique to reduce the cost and improve the accuracy of the dynamics model for the vehicle.

Off-road tire modeling and the multi-pass effect for vehicle dynamics simulation

Off-road operations are critical in many fields and the complexity of the tire-terrain interaction deeply affects vehicle performance. In this paper, a semi-empirical off-road tire model is discussed. The efforts of several researchers are brought together into a single model able to predict the main features of a tire operating in off-road scenarios by computing drawbar pull, driving torque, lateral force, slip-sinkage phenomenon and the multi-pass behavior. The approach is principally based on works by Wong, Reece, Chan, and Sandu and it is extended in order to catch into a single model the fundamental features of a tire running on soft soil. A thorough discussion of the methodology is conducted in order to highlight strengths and weakness of different implementations. The study considers rigid wheels and flexible tires and analyzes the longitudinal and the lateral dynamics. Being computationally inexpensive a semi-empirical model is attractive for real time vehicle dynamics simulations. To the best knowledge of the authors, current vehicle dynamics codes poorly account for off-road operations where tire-terrain interaction dominates vehicle performance. In this paper two soils are considered: a loose sandy terrain and a firmer loam. Results show that the model realistically predicts longitudinal and lateral forces providing at the same time good estimates of the slip-sinkage behavior and tire parameters sensitivity.

Techniques tor autonomous, off-road navigation

To extend autonomous navigation to unpaved and off-road scenarios, vehicles in the AutoNav program bolster a 4D perception and control architecture with area-based vision techniques. This article describes how an autonomous vehicle uses directed real-time, area-based, stereo processing to determine the vertical profile of its path.

An Efficient Three-Dimensional Tire Model for Vehicle Dynamics Simulations*

ABSTRACT For vehicle dynamics simulations, tire models are lacking that can accurately predict spindle loads resulting from durability road events, such as curb impact or chuckhole impact, and for off-road scenarios. In this paper, an efficient three-dimensional tire model is presented for use in simulating such events. The model is based upon a precomputed table that characterizes the force-deflection behavior of the tire sidewall, which is coupled to standard shell elements to model the tire tread. Comparisons are given between computed and experimental results for several different loading cases that demonstrate the effectiveness of the proposed model