Diffusion-Based Reconstruction of 3-D Occupancy Maps From 4-D Radar Tensors

We develop a new occupancy map that respects the role of the sensor measurement bearing and how it relates to the resolution of the existing occupancy map. We borrow an idea from Konolige for recording and tracking, in an occupancy-like map, the bearing at which sensor readings originate with respect to a given cell. Our specific contribution is in the way we process the sensor pose information, which is the bearing of the sensor readings when it indicates the presence of an obstacle in a particular cell. For each cell in the occupancy map, we calculate the greatest separation of incident poses, and then store that information in a new two-dimensional array called a pose map. A cell in the pose map measures the quality of information contained in the corresponding cell of the occupancy map. We merge the new pose map with the existing map to generate an enhanced occupancy map. Exploration plans derived from the enhanced occupancy map are more efficient and complete in that they do not guide the robot around phantom obstacles nor incorrectly classify narrow openings as closed commonly found in conventional occupancy maps.

Occupancy mapping is an important component of a robot navigation system since it enables intelligent planning of actions to accomplish a task. In some cases, occupancy information is mapped as part of a SLAM system. In other cases, such as visual SLAM, an occupancy map must be separately created, harnessing localization information. We present a novel occupancy mapping method that adaptively and efficiently takes advantage of improved trajectory estimates from the localization system, without requiring storage of all poses of the trajectory or the sensor information from all poses. Occupancy information is stored in local maps anchored to poses in the trajectory. Local maps are created adaptively depending on the uncertainty of localization. The local maps maintain consistency of occupancy information independently of changes in the localization map due to loop closures or convergence of the estimation algorithm. At any time, a global occupancy map (snapshot map) can be rendered from the local occupancy maps. We evaluate the performance of the system using real data and compare it to two baseline methods.

Path planners are generally categorised as either trajectory optimisers or sampling-based planners. The latter is the predominant planning paradigm for occupancy maps. Most trajectory optimisers require a fully defined artificial potential field for planning and cannot incorporate updates from a partially observed model such as an occupancy map. A stochastic trajectory optimiser capable of planning over occupancy map was presented in [1]. However, its scalability is limited by the cubic complexity of the Gaussian process path representation. In this work, we introduce a novel highly expressive path representation based on kernel approximation to perform trajectory optimisation over occupancy maps. This approach reduces the computational complexity to a fixed cost that only depends on the number of features. We show that stochastic sampling is crucial for planning in occupancy maps and present comparisons to other state-of-the-art planning methods, using simulated and real occupancy data. These experiments demonstrate the significant reduction in runtime, resulting in performance comparable to or better than sampling-based methods.

In the UK, increased levels of developer funding has led to increased demand for archaeological fieldworkers, the producers of the primary data upon which all archaeological work and research depends. But archaeologists entering the profession are underskilled while increasing numbers of students are receiving archaeological degrees, recent graduates do not have the levels of practical knowledge that are required to work on major projects. This skills shortage is not restricted to junior fieldstaff. Throughout the profession there is a lack of structured vocational learning, and training is undervalued both by organisations and individuals. This article discusses archaeologists' engagement with the challenge of creating a skilled archaeological profession in the UK. The Institute of Field Archaeologists (IFA), as the professional association for all archaeologists in the UK, advocates the development of a co-ordinated training structure in archaeology which connects skills across a range of disciplines with formally recognised qualifications and defined professional roles. It envisages that this structure should have the potential for a link with pay and conditions and could lead to the development of a stronger career structure in professional archaeology. The IFA has set out an agenda, identifying that structured training is required in terms of basic training (e.g. for undergraduates); entry-level (equipping graduates for the workplace) and progressive training through continuing professional development (enabling practitioners to progress in their careers by maintaining and updating their skills). This recognises that it is widely accepted that the status of a professional depends upon his or her skills, and the qualifications that ratify those skills. The mechanism by which a professional is able to maintain and update their skills is continuing professional development; the IFA's guidance on continuing professional development establishes that it is the professional obligation of an individual archaeologist to maintain and update their skills, but this is anticipated to move towards a system whereby this will become a mandatory requirement for members of the professional institute. To date, the IFA has launched a series of projects under the auspices of the Archaeology Training Forum (ATF) to address the issue of training in professional archaeology. Potentially the most significant of these is a project to define professional functions and skills. This has identified the specific (archaeological) and generic skills archaeologists need. It has produced an 'occupational map' of archaeology, which will enable people to see where they are on that map (in terms of the role they fulfil and the skills they have) and to identify the role or roles that they want to fulfil in the profession - and the skills that they need to get there. It is anticipated that a structure of formal vocational qualifications, in combination with informal learning frameworks (including opportunities for focused coaching and mentoring) will emerge from this project. Currently the ATF is endorsing specific courses that aim to meet recognised needs within archaeology, and some of these have then been subsidised by the national heritage agencies, presenting opportunities for archaeologists at all stages of their careers. TORC, a training course web portal, providing information on all archaeological courses running in the UK, has been established by the Council for British Archaeology. To have a trained and skilled workforce would enhance and guarantee the quality of the work being undertaken by archaeologists, presenting ways that archaeology can be shown to provide better value for the other stakeholders in archaeologists' work. This would also lead to the retention of that workforce, forming a key step on the route to the development of a career structure within professional archaeology.

This paper proposed an efficient method to provide a robust occupancy grid useful for robot navigation tasks. An omnidirectional indoor robot accomplishing logistics tasks, has been equipped with stereocameras for detecting the presence of moving and fixed obstacles. The stereocamera provides a 3D point cloud. Starting from the tridimensional information, the occupancy map can be computed. Nevertheless, the point cloud often owns unstable points mainly due to low accurate disparity map and to light reflections on the floor that produce mismatching during the stereo matching phase. The point cloud has been opportunely filtered by using a cascade approach in order to get more robust occupancy grids. Passthrough filters are applied to remove the too far 3D points. Since high reflective floors produce unwanted 3D points, a color filter is also used to remove those points having saturated intensity values. The remaining floating points related always to the floor are then filtered out by taking advantage of the knowledge about the camera tilt. At this stage, a preliminary 2D occupancy grid is built to sample the point cloud. Each bin of occupancy map is then processed. In case the cell under investigation contains points, a distribution analysis about the point spread is performed. If the height of the highest point is under a determined threshold value, the cell value is set to zero. The unwanted floor points are thus furtherly removed. The cells containing a low number of points are also cleared. Finally, the isolated cells of occupancy grid and the cells that do not have enough valid neighboring cells are reset. The noisy points and the edge points of objects do not concur to produce inaccurate occupancy maps. Final outcomes prove as the proposed methodology enables to provide robust occupancy maps ensuring high performance in terms of processing time.

Occupancy maps are a standard method for probabilistic spatial representations of the environment of a mobile robot. They are easy to build and maintain and suffice for many navigation tasks. However, for solving more complex tasks the need to integrate metric occupancy maps with topological or relational spatial information arises. An important step in the automatic extraction of symbolic representations from sub-symbolic data such as occupancy maps is the segmentation of occupancy maps into areas with similar occupancy. Formerly suggested methods usually lead to unintuitive segmentation, which are difficult to match with symbolic concepts like rooms or hallways. We present the wall histogram method which makes use of the concepts and algorithms developed in computer vision, to yield more intuitive occupancy map segmentation.

In video-based point cloud compression (V-PCC), occupancy map video is utilized to indicate whether a 2-D pixel corresponds to a valid 3-D point or not. In the current design of V-PCC, the occupancy map video is directly compressed losslessly with High Efficiency Video Coding (HEVC). However, the coding tools in HEVC are specifically designed for natural images, thus unsuitable for the occupancy map. In this paper, we present a novel quadtree-based scheme for lossless occupancy map coding. In this scheme, the occupancy map is firstly divided into several coding tree units (CTUs). Then, the CTU is divided into coding units (CUs) recursively using a quadtree. The quadtree partition is terminated when one of the three conditions is satisfied. Firstly, all the pixels have the same value. Secondly, the pixels in the CU only have two kinds of values and they can be separated by a continuous edge whose endpoints lie on the side of the CU. The continuous edge is then coded using chain code. Thirdly, the CU reaches the minimum size. This scheme simplifies the design of block partitioning in HEVC and designs simpler yet more effective coding tools. Experimental results show significant reduction of bit-rate and complexity compared with the occupancy map coding scheme in V-PCC. In addition, this scheme is also very efficient to compress the semantic map.

We present a dense volumetric simultaneous localisation and mapping (SLAM) framework that uses an octree representation for efficient fusion and rendering of either a truncated signed distance field (TSDF) or an occupancy map. The primary aim of this letter is to use one single representation of the environment that can be used not only for robot pose tracking and high-resolution mapping, but seamlessly for planning. We show that our highly efficient octree representation of space fits SLAM and planning purposes in a real-time control loop. In a comprehensive evaluation, we demonstrate dense SLAM accuracy and runtime performance on-par with flat hashing approaches when using TSDF-based maps, and considerable speed-ups when using occupancy mapping compared to standard occupancy maps frameworks. Our SLAM system can run at 10–40 Hz on a modern quadcore CPU, without the need for massive parallelization on a GPU. We, furthermore, demonstrate a probabilistic occupancy mapping as an alternative to TSDF mapping in dense SLAM and show its direct applicability to online motion planning, using the example of informed rapidly-exploring random trees (RRT $^*$ ).

The concepts of occupancy grids and probabilistic maps were introduced at the end of the eighties. Since then, research work focused mainly on the definition of the representation, data fusion and generation of occupancy models. Few consideration has been given to processing occupancy maps as textured images in order to extract meaningful information required for robot navigation and control of interactions with the environment. This paper investigates the application of segmentation techniques on probabilistic occupancy maps represented as textured images. Enhancements are proposed to a uniformity estimation technique based on local binary pattern and contrast (LBP/C) to achieve robust segmentation of occupancy maps that typically result from range sensors with limited resolution. The accuracy of the segmented 2D occupancy maps is demonstrated experimentally through an application on mobile robot navigation with collision avoidance

An occupancy map provides an abstract top view of a scene and can be used for many applications such as domotics, surveillance, elderly-care and video teleconferencing. Such maps can be accurately estimated from multiple camera views. However, using a network of regular high resolution cameras makes the system expensive, and quickly raises privacy concerns (e.g. in elderly homes). Furthermore, their power consumption makes battery operation difficult. A solution could be the use of a network of low resolution visual sensors, but their limited resolution could degrade the accuracy of the maps. In this paper we used simulations to determine the minimum required resolution needed for deriving accurate occupancy maps which were then used to track people. Multi-view occupancy maps were computed from foreground silhouettes derived via an analysis of moving edges. Ground occupancies computed from each view were fused in a Dempster-Shafer framework. Tracking was done via a Bayes filter using the occupancy map per time instance as measurement. We found that for a room of 8.8 by 9.2 m, 4 cameras with a resolution as low as 64 by 48 pixels was sufficient to estimate accurate occupancy maps and track up to 4 people. These findings indicate that it is possible to use low resolution visual sensors to build a cheap, power efficient and privacy-friendly system for occupancy monitoring.

We present a novel approach for enhancing robotic exploration by using generative occupancy mapping. We implement SceneSense, a diffusion model designed and trained for predicting 3D occupancy maps given partial observations. Our proposed approach probabilistically fuses these predictions into a running occupancy map in real-time, resulting in significant improvements in map quality and traversability. We deploy SceneSense on a quadruped robot and validate its performance with real-world experiments to demonstrate the effectiveness of the model. In these experiments we show that occupancy maps enhanced with SceneSense predictions better estimate the distribution of our fully observed ground truth data (24.44% FID improvement around the robot and 75.59% improvement at range). We additionally show that integrating SceneSense enhanced maps into our robotic exploration stack as a “drop-in” map improvement, utilizing an existing off-the-shelf planner, results in improvements in robustness and traversability time. Finally, we show results of full exploration evaluations with our proposed system in two dissimilar environments and find that locally enhanced maps provide more consistent exploration results than maps constructed only from direct sensor measurements.

This paper proposes a new method for occupancy map building using a mixture of Gaussian processes. We consider occupancy maps as a binary classification problem of positions being occupied or not, and apply Gaussian processes. Particularly, since the computational complexity of Gaussian processes grows as O(n3), where n is the number of data points, we divide the training data into small subsets and apply a mixture of Gaussian processes. The procedure of our map building method consists of three steps. First, we cluster acquired data by grouping laser hit points on the same line into the same cluster. Then, we build local occupancy maps by using Gaussian processes with clustered data. Finally, local occupancy maps are merged into one by using a mixture of Gaussian processes. Simulation results will be compared with previous researches and provided demonstrating the benefits of the approach.

The concepts of occupancy grids and probabilistic maps were introduced at the end of the eighties. Since then, research work focussed mainly on the definition of the representation, data fusion and generation of occupancy models. Few consideration has been given to processing occupancy maps as textured images in order to extract meaningful information required for robot navigation and control of interactions with the environment. This paper investigates the application of segmentation techniques on probabilistic occupancy maps represented as textured images. Enhancements are proposed to a uniformity estimation technique based on local binary pattern and contrast (LBP/C) to achieve robust segmentation of occupancy maps that typically result from range sensors with limited resolution. The accuracy of the segmented 2D occupancy maps is demonstrated experimentally through an application on mobile robot navigation with collision avoidance.

This paper proposes a novel method for occupancy map building using a mixture of Gaussian processes. Gaussian processes have proven to be highly flexible and accurate for a robotic occupancy mapping problem, yet the high computational complexity has been a critical barrier for large-scale applications. We consider clustering the data into small, manageable subsets and applying a mixture of Gaussian processes. One of the problems in clustering is that the number of groups is not known a priori, thus requiring inputs from experts. We propose two efficient clustering methods utilizing (1) a Dirichlet process and (2) geometrical information in the context of occupancy mapping. We will show that the Dirichlet process-based clustering can significantly speed up the training step of the Gaussian process and if geometrical features, such as line features, are available, they can further improve the clustering accuracy. We will provide simulation results, analyze the performance and demonstrate the benefits of the proposed methods.

We describe an algorithm to fuse intensity data from multiple video cameras to create a spatial-temporal occupancy map. The camera layout is assumed to resemble a security video network. The occupancy map is a two-dimensional raster image, uniformly distributed in the floor-plane. Each map pixel contains a binary value, signifying whether the designated floorspace is empty or occupied. Our algorithm requires only one difference and one look-up table operation to determine each pixel's effect upon the map. This brevity of operations allows the spatial occupancy map to be temporally computed at real-time video rates. We demonstrate our algorithm operating in several dynamic scenarios.