Conference Paper

Efficient Grid Map Data Structures for Autonomous Driving in Large-Scale Environments

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Here, layers with a road have higher cell resolutions than other layers at the same distance. [9]. By altering the number of cells allocated at a time, these strategies mainly try to reduce computational expenses. ...
... In this work, however, the focus is on improving the underlying grid map structure rather than the dynamic occupancy estimation. Similarly, recent approaches proposed new grid map structures and analyzed the implementation impact on efficiency [8], [9]. Retaining a moving grid, the authors of [8] proposed a method to reduce the cell resolution for the far field of the environment. ...
... Thus, all possible requirements must be met with a single layout, and requirement changes can not lead to further improvements. In contrast, the authors of [9] proposed different ways of dividing the environment into sub-maps first. In principle, this would allow reacting dynamically on external requirements. ...
Preprint
Full-text available
In this work, we propose a novel adaptive grid mapping approach, the Adaptive Patched Grid Map, which enables a situational aware grid based perception for autonomous vehicles. Its structure allows a flexible representation of the surrounding unstructured environment. By splitting types of information into separate layers less memory is allocated when data is unevenly or sporadically available. However, layers must be resampled during the fusion process to cope with dynamically changing cell sizes. Therefore, we propose a novel spatial cell fusion approach. Together with the proposed fusion framework, dynamically changing external requirements, such as cell resolution specifications and horizon targets, are considered. For our evaluation, real-world data were recorded from an autonomous vehicle driving through various traffic situations. Based on this, the memory efficiency is compared to other approaches, and fusion execution times are determined. The results confirm the adaptation to requirement changes and a significant memory usage reduction.
... This is implemented by using a hierarchical map organization, which can be seen in Fig. 4. The map is split into submaps, which are allocated or discarded according to the movement of the vehicle. The equations as well as a performance evaluation for different underlying datastructures can be found in [21]. ...
... The currently active window is shown as a blue outline in two timesteps. As the vehicle moves, the submaps behind it are discarded (red crosses), and new ones are allocated in the direction of travel (green outlines), from[21]. ...
... File systems on computers are mostly organized in tree structures. • Grids [7] are structures that divide the environment into a grid of equally sized cells. ...
Article
Full-text available
Presenting real-world paths in property graphs is a complex challenge of identifying and representing the properties of routes and their environments. These property graphs serve as foundational datasets for generating smart sports training routes, where route features such as terrain, bends, and hills critically influence the route design. This paper outlines a method for identifying key parameters of real-world paths and encoding them into property graphs. The proposed method has significant implications for sports event planning, particularly in designing route-based training that meets specific athletic challenges. The research concludes by presenting a case study in which a property graph that enables cycling route generation was created for the country of Slovenia, and a sample training route was generated.
... The field of grid mapping is an active research area, especially efficient grid mapping gets more and more interesting. There are already works about non-uniform grid and cell resolution [231] and a special patch structure to accelerate particularly the computation time [232]. One of the major challenges in this area so far is the flexibility of performing a grid map with online adaptable configurations. ...
Article
Full-text available
Nowadays, many intelligent vehicles are equipped with various sensors to recognize their surrounding environment and to measure the motion or position of the vehicle. In addition, the number of intelligent vehicles equipped with a mobile Internet modem is increasing. Based on the sensors and Internet connection, the intelligent vehicles are able to share the sensor information with other vehicles via a cloud service. The sensor information sharing via the cloud service promises to improve the safe and efficient operation of the multiple intelligent vehicles. This paper presents a cloud update framework of occupancy grid maps for multiple intelligent vehicles in a large-scale environment. An evidential theory is applied to create the occupancy grid maps to address sensor disturbance such as measurement noise, occlusion and dynamic objects. Multiple vehicles equipped with LiDARs, motion sensors, and a low-cost GPS receiver create the evidential occupancy grid map (EOGM) for their passing trajectory based on GraphSLAM. A geodetic quad-tree tile system is applied to manage the EOGM, which provides a common tiling format to cover the large-scale environment. The created EOGM tiles are uploaded to EOGM cloud and merged with old EOGM tiles in the cloud using Dempster combination of evidential theory. Experiments were performed to evaluate the multiple EOGM mapping and the cloud update framework for large-scale road environment.
Article
Full-text available
This paper presents a GPU-based wave-front propagation technique for multi-agent path planning in extremely large, complex, dynamic environments. Our work proposes an adaptive subdivision of the environment with efficient indexing, update, and neighbor-finding operations on the GPU to address several known limitations in prior work. In particular, an adaptive environment representation reduces the device memory requirements by an order of magnitude which enables for the first time, GPU-based goal path planning in truly large-scale environments (> 2048 m2 ) for hundreds of agents with different targets. We compare our approach to prior work that uses an uniform grid on several challenging navigation benchmarks and report significant memory savings, and up to a 1000X computational speedup.
Article
Full-text available
Grid mapping is a well established approach for environment perception in robotic and automotive applications. Early work suggests estimating the occupancy state of each grid cell in a robot's environment using a Bayesian filter to recursively combine new measurements with the current posterior state estimate of each grid cell. This filter is often referred to as binary Bayes filter (BBF). A basic assumption of the BBF is a stationary environment. Recent publications describe bottom-up approaches using particles to represent the dynamic state of a grid cell and outline prediction-update recursions in a heuristic manner. This paper defines the state of multiple grid cells as a random finite set, which allows to model the environment as a stochastic, dynamic system with multiple obstacles, observed by a stochastic measurement system. It motivates an original filter called the probability hypothesis density / multi-instance Bernoulli (PHD/MIB) filter in a top-down manner. The paper presents a real-time application serving as a fusion layer for laser and radar sensor data and describes in detail a highly efficient parallel particle filter implementation. A quantitative evaluation shows that parameters of the stochastic process model affect the filter results as theoretically expected and that appropriate process and observation models provide consistent state estimation results.
Article
Full-text available
This article provides an elaborate overview of current research in extended object tracking. We provide a clear definition of an extended object and discuss its delimitation to other object types and sensor models. Next, different shape models and possibilities to model the number of measurements are extensively discussed. Subsequently, we give a tutorial introduction to two basic and well used extended object tracking methods -- the random matrix approach and random hypersurface approach. The next part treats approaches for tracking multiple extended objects and elaborates how the large number of feasible association hypotheses can be tackled using both Random Finite Set (RFS) and Non-RFS multi-object trackers. The article concludes with a summary of current applications, where three example applications involving Lidar, RGB, and RGB-D sensors are highlighted.
Conference Paper
Full-text available
This paper presents a GPU-based wave-front propagation technique for multi-agent path planning in extremely large, complex, dynamic environments. Our work proposes an adaptive subdivision of the environment with efficient indexing, update, and neighbor-finding operations on the GPU to address several known limitations in prior work. In particular, an adaptive environment representation reduces the device memory requirements by an order of magnitude which enables for the first time, GPU-based goal path planning in truly large-scale environments (>2048> 2048 m2m^2) for hundreds of agents with different targets. We compare our approach to prior work that uses an uniform grid on several challenging navigation benchmarks and report significant memory savings, and up to a 1000X computational speedup.
Article
Full-text available
Modeling and tracking the driving environment is a complex problem due to the heterogeneous nature of the real world. In many situations, modeling the obstacles and the driving surfaces can be achieved by the use of geometrical objects, and tracking becomes the problem of estimating the parameters of these objects. In the more complex cases, the scene can be modeled and tracked as an occupancy grid. This paper presents a novel occupancy grid tracking solution based on particles for tracking the dynamic driving environment. The particles will have a dual nature-they will denote hypotheses, as in the particle filtering algorithms, but they will also be the building blocks of our modeled world. The particles have position and speed, and they can migrate in the grid from cell to cell, depending on their motion model and motion parameters, but they will be also created and destroyed using a weighting-resampling mechanism that is specific to particle filtering algorithms. The tracking algorithm will be centered on particles, instead of cells. An obstacle grid derived from processing a stereovision-generated elevation map is used as measurement information, and the measurement model takes into account the uncertainties of the stereo reconstruction. The resulting system is a flexible real-time tracking solution for dynamic unstructured driving environments.
Article
Full-text available
We examine the problem of constructing and maintaining a map of an autonomous vehicle's environment for the purpose of navigation, using evidential reasoning. The inherent uncertainty in the origin of measurements of sensors demands a probabilistic approach to processing, or fusing, the new sensory information to build an accurate map. In the paper, the map is based on a two-dimensional (2-D) occupancy grid. The sensor readings are fused into the map using the Dempster-Shafer inference rule. This evidential approach with its multivalued hypotheses allows quantitative analysis of the quality of the data. The map building system is experimentally evaluated using sonar data from real environments
Article
Full-text available
An approach to robot perception and world modeling that uses a probabilistic tesselated representation of spatial information called the occupancy grid is reviewed. The occupancy grid is a multidimensional random field that maintains stochastic estimates of the occupancy state of the cells in a spatial lattice. To construct a sensor-derived map of the robot's world, the cell state estimates are obtained by interpreting the incoming range readings using probabilistic sensor models. Bayesian estimation procedures allow the incremental updating of the occupancy grid, using readings taken from several sensors over multiple points of view. The use of occupancy grids from mapping and for navigation is examined. Operations on occupancy grids and extensions of the occupancy grid framework are briefly considered.< >
Article
Full-text available
We propose a new approach to collision and self-- collision detection of dynamically deforming objects that consist of tetrahedrons. Tetrahedral meshes are commonly used to represent volumetric deformable models and the presented algorithm is integrated in a physically--based environment, which can be used in game engines and surgical simulators. The proposed algorithm employs a hash function for compressing a potentially infinite regular spatial grid. Although the hash function does not always provide a unique mapping of grid cells, it can be generated very efficiently and does not require complex data structures, such as octrees or BSPs. We have investigated and optimized the parameters of the collision detection algorithm, such as hash function, hash table size and spatial cell size. The algorithm can detect collisions and self-- collisions in environments of up to 20k tetrahedrons in real--time. Although the algorithm works with tetrahedral meshes, it can be easily adapted to other object primitives, such as triangles.
Conference Paper
Control, tracking, and obstacle detection algorithms for mobile robots, including autonomous cars, rely on a jump-free estimate of the vehicle's pose. While one cannot completely avoid jumps in global solutions like INS/GNSS and SLAM, relative localization (i.e., odometry) does not suffer from this problem. Methods based on graph optimization are popular in that field, but they do not scale very well with high-frequency measurements. Kalman filters (KFs) are able to cope with those measurements, but they face the issue of a continuously growing covariance. This results in instabilities and eventually jumps in the state estimate. We present an approach to handle this problem by periodically moving the reference state forward in time, which is realized using two filters. The equations for implementing this in both the extended Kalman filter (EKF) and the unscented Kalman filter (UKF) are derived. The algorithm is evaluated using real-world datasets covering different scenarios of autonomous driving. We show that our method provides a smooth and stable estimate even over long time periods and that it achieves a better localization performance than the standard approach.
Article
Algorithms for controlling fully autonomous systems must meet especially high requirements with respect to safety and robustness. A particularly challenging example are autonomous deep space missions, which we investigated in several projects. In this context, we showed that a safe and robust autonomous system can be realized through nonlinear model predictive control approaches using optimization techniques in combination with multi-sensor fusion based on an extended representation of uncertainty. The focus of this paper is on demonstrating the versatility of that concept by transferring the corresponding algorithms to the also very challenging application of autonomous driving. In particular, we propose a system concept for a self-driving car based on our methodology. Furthermore, we present results of a real world research vehicle that autonomously explores a parking lot, dynamically takes obstacles into account, and finally performs a parking maneuver.
Article
Modeling and estimating the current local environment by processing sensor measurement data is essential for intelligent vehicles. Static obstacles, dynamic objects, and free space have to be appropriately represented, classified, and filtered. Occupancy grids, known for mapping static environments, provide a common low-level representation using occupancy probabilities with an implicit data association through the discrete grid structure. Extending this idea toward dynamic environments with moving objects requires a static/dynamic classification of measured occupancy and a tracking of the dynamic state of grid cells. In this work, we propose a new dynamic grid mapping approach. An evidential representation using the Dempster-Shafer framework is used to model hypotheses for static occupancy, dynamic occupancy, free space, and their combined hypotheses. These hypotheses are consistently estimated and accumulated in a dynamic grid map by an adapted evidential filtering, allowing one to distinguish static and dynamic occupancy. The evidential grid mapping is combined with a low-level particle filter tracking that is used to estimate cell velocity distributions and predict dynamic occupancy of the grid map. Static occupancy is directly modeled in the grid map without requiring particles, increasing efficiency and improving the static/dynamic classification due to the persistent map accumulation. Experimental results with real sensor data show the effectiveness of the proposed approach in challenging scenarios with occlusions and dense traffic.
Conference Paper
The occupancy grid mapping technique is widely used for environmental mapping of moving vehicles. Occupancy grid maps with fixed cell size have been extended using the quadtree implementation with adaptive cell size. Adaptive grid maps have proven to be more resource efficient than fixed cell size grid maps. Dynamic cell sizes introduce the necessity of a split and merge process to trigger the refinement of grid cells. This paper presents a novel ray-based refinement process in order to choose the appropriate resolution for the sensor observation. Based on measurement conflicts some approaches use an iterative refinement process until all conflicts are solved. In contrast this paper presents an non-iterative approach based on the sensor resolution. Using the measurement data efficiently we propose an algorithm, which solves the problem of partially free cells in an adaptive grid map. The proposed algorithm is compared against other widely used algorithms and methodologies.
Conference Paper
Autonomous vehicles operating in real-world industrial environments have to overcome numerous challenges, chief among which are the creation of consistent 3D world models and the simultaneous tracking of the vehicle pose with respect to the created maps. In this paper we integrate two recently proposed algorithms in an online, near-realtime mapping and tracking system. Using the Normal Distributions Transform (NDT), a sparse Gaussian Mixture Model, for representation of 3D range scan data, we propose a frame-to-model registration and data fusion algorithm - NDT Fusion. The proposed approach uses a submap indexing system to achieve operation in arbitrarily-sized environments. The approach is evaluated on a publicly available city-block sized data set, achieving accuracy and runtime performance significantly better than current state of the art. In addition, the system is evaluated on a data set covering ten hours of operation and a trajectory of 7.2km in a real-world industrial environment, achieving centimeter accuracy at update rates of 5-10 Hz.
Book
This well-accepted introduction to computational geometry is a textbook for high-level undergraduate and low-level graduate courses. The focus is on algorithms and hence the book is well suited for students in computer science and engineering. Motivation is provided from the application areas: all solutions and techniques from computational geometry are related to particular applications in robotics, graphics, CAD/CAM, and geographic information systems. For students this motivation will be especially welcome. Modern insights in computational geometry are used to provide solutions that are both efficient and easy to understand and implement. All the basic techniques and topics from computational geometry, as well as several more advanced topics, are covered. The book is largely self-contained and can be used for self-study by anyone with a basic background in algorithms. In this third edition, besides revisions to the second edition, new sections discussing Voronoi diagrams of line segments, farthest-point Voronoi diagrams, and realistic input models have been added.
Optimized spatial hashing for collision detection of deformable objects
  • M Teschner
  • B Heidelberger
  • M Müller
  • D Pomerantes
  • M H Gross