Traversal Cost Research Articles

Autonomous Vehicles Traversability Mapping Fusing Semantic–Geometric in Off-Road Navigation

This paper proposes an evaluating and mapping methodology of terrain traversability for off-road navigation of autonomous vehicles in unstructured environments. Terrain features are extracted from RGB images and 3D point clouds to create a traversal cost map. The cost map is then employed to plan safe trajectories. Bayesian generalized kernel inference is employed to assess unknown grid attributes due to the sparse raw point cloud data. A Kalman filter also creates density local elevation maps in real time by fusing multiframe information. Consequently, the terrain semantic mapping procedure considers the uncertainty of semantic segmentation and the impact of sensor noise. A Bayesian filter is used to update the surface semantic information in a probabilistic manner. Ultimately, the elevation map is utilized to extract geometric characteristics, which are then integrated with the probabilistic semantic map. This combined map is then used in conjunction with the extended motion primitive planner to plan the most effective trajectory. The experimental results demonstrate that the autonomous vehicles obtain a success rate enhancement ranging from 4.4% to 13.6% and a decrease in trajectory roughness ranging from 5.1% to 35.8% when compared with the most developed outdoor navigation algorithms. Additionally, the autonomous vehicles maintain a terrain surface selection accuracy of over 85% during the navigation process.

Environmental force sensing helps robots traverse cluttered large obstacles

Robots can traverse sparse obstacles by sensing environmental geometry and avoiding contact with obstacles. However, for search and rescue in rubble, environmental monitoring through dense vegetation, and planetary exploration over Martian and lunar rocks, robots must traverse cluttered obstacles as large as themselves by physically interacting with them. Previous work discovered that the forest floor-dwelling discoid cockroach and a sensor-less minimalistic robot can traverse cluttered grass-like beam obstacles of various stiffness by transitioning across different locomotor modes. Yet the animal was better at traversal than the sensor-less robot, likely by sensing forces during obstacle interaction to control its locomotor transitions. Inspired by this, here we demonstrated in simulation that environmental force sensing helps robots traverse cluttered large obstacles. First, we developed a multi-body dynamics simulation and a physics model of the minimalistic robot interacting with beams to estimate beam stiffness from the sensed contact forces. Then, we developed a force feedback strategy for the robot to use the sensed beam stiffness to choose the locomotor mode with a lower mechanical energy cost. With feedforward pushing, the robot was stuck in front of stiff beams if it has a limited force capacity; without force limit, it traversed but suffered a high energy cost. Using obstacle avoidance, the robot traversed beams by avoiding beam contact regardless of beam stiffness, resulting in a high energy cost for flimsy beams. With force feedback, the robot determined beam stiffness, then traversed flimsy beams by pushing them over and stiff beams by rolling through the gap between them with a low energy cost. Stiffness estimation based on force sensing was accurate across varied body oscillation amplitude and frequency and position sensing uncertainty. Mechanical energy cost of traversal increased with sensorimotor delay. Future work should demonstrate cluttered large obstacle traversal using force feedback in a physical robot.

Understanding the Visual Relationship between Function and Facade in Historic Buildings Using Deep Learning—A Case Study of the Chinese Eastern Railway

Although functional identifiability represents a key aspect for promoting visual connotation and sustainable usability in historic building groups, there is still no consensus on how to quantitatively describe its identification basis at a large scale. The recent emergence of the potentiality of deep learning and computer vision has provided an alternative to traditional empirical-based judgment, which is limited by its subjective bias and high traversal costs. To address these challenges, this study aims to build a workflow for a visual analysis of function and facade to extract the different contributions that facade elements provide to functional expression. The approach is demonstrated with an experiment on a section of the Chinese Eastern Railway (CER) where large-scale historical buildings images were categorized to identify functions using deep learning, together with activation and substance for visual calculations. First, the dataset aggregated with images of historic buildings along the CER was used to identify functional categories using SE-DenseNet merging channel attention. The results of the model visualized using t-SNE and Grad-CAM were then used to analyze the relationships of facade features across functional categories and differences in elemental feature representation across functional prototypes. The results show the following: (1) SE-Densenet can more efficiently identify building functions from the closely linked facade images of historic building groups, with the average accuracy reaching 85.84%. (2) Urban–rural differences exist not only in the count of spatial distributions among the CER’s historic building groups, but also in a significant visual divergence between functions related to urban life and those involved in the military, industry, and railways. (3) Windows and walls occupy areas with more characteristics, but their decorative elements have a higher intensity of features. The findings could enhance the objective understanding and deeper characteristics of the historical building group system, contributing to integrated conservation and characteristic sustainability.

Optimal Pathfinding on Weighted Grid Maps

In many computer games up to hundreds of agents navigate in real-time across a dynamically changing weighted grid map. Pathfinding in these situations is challenging because the grids are large, traversal costs are not uniform, and because each shortest path has many symmetric permutations, all of which must be considered by an optimal online search. In this work we introduce Weighted Jump Point Search (JPSW), a new type of pathfinding algorithm which breaks weighted grid symmetries by introducing a tiebreaking policy that allows us to apply effective pruning rules in symmetric regions. We show that these pruning rules preserve at least one optimal path to every grid cell and that their application can yield large performance improvements for optimal pathfinding. We give a complete theoretical description of the new algorithm, including pseudo-code. We also conduct a wide-ranging experimental evaluation, including data from real games. Results indicate JPSW is up to orders of magnitude faster than the nearest baseline, online search using A*.

Upgrading edges in the Graphical TSP

In this paper we present a generalization of the Graphical Traveling Salesman Problem (GTSP). Given a communication graph in which not all direct connections are necessarily possible, the Graphical Traveling Salesman Problem consists of finding the shortest tour that visits each node at least once. In this work, we assume the availability of a budget that allows to upgrade, i.e. reduce their traversal cost, some of the current connections and we propose the problem of designing the minimum cost tour using this budget. We propose and study a formulation for the problem, verifying that the polyhedron associated with the set of feasible solutions of a relaxed version of the problem is a full-dimensional polytope. We present families of valid inequalities that reinforce the model and pre-processing techniques to reduce the number of variables of the formulation. To solve the problem, we propose a branch-and-cut algorithm that uses the introduced valid inequalities, as well as a heuristic to obtain good upper bounds and a tailor-made branching strategy. Comprehensive computational experiments on a new set of benchmark instances are presented to assess the performance of this exact method.

An autonomous navigation approach for unmanned vehicle in off-road environment with self-supervised traversal cost prediction

An autonomous navigation approach for unmanned vehicle in off-road environment with self-supervised traversal cost prediction

Challenges in Integrating Low-level Path Following and High-level Path Planning Over Polytopic Maps

Autonomous vehicle navigation and control require both planning and successful following of a desired path through an environment. This is often performed by a hierarchical framework that includes both a path planning algorithm and a path following controller. However, these two levels often operate with different modeling assumptions, constraints, and cost functions, leading to several challenges when integrated. To demonstrate the challenges that arise specifically when mapped obstacles represent regions that can be traversed but with varying traversal costs, this paper builds an intuitive control hierarchy consisting of an A* path planner, a Kalman filter to estimate traversal costs, and a model predictive controller. While each of these elements have been deeply studied individually, this paper identifies challenges that can arise from their coupled behavior and categories existing literature that addresses some of these challenges. Simulation results for a ground vehicle traversing regions of varying cost illustrate both the benefits and potential pitfalls of this hierarchical integration, motivating its further study for vehicle autonomy.

A dense obstacle avoidance algorithm for UAVs based on safe flight corridor

Aiming at the problem of autonomous obstacle avoidance of fixed-wing UAVs in a complex, dense and multi-obstacle environment, a path planning algorithm for fixed-wing UAVs based on a safe flight corridor is proposed. The difficulty of avoiding dense obstacles lies in the choice of obstacle circumvention and traversal: although circumvention is safer, the flight cost is greater; although the traversal cost is lower, the safety threat is higher. How to quickly solve the optimal path is the core issue. This paper firstly defines a safe flight corridor innovatively based on the maneuvering characteristics of fixed-wing UAVs and the Dubins curves. By comprehensively considering UAV flight safety and flight costs, an obstacle threat evaluation function is constructed. Secondly, in view of the computational complexity caused by the dense obstacles, an obstacle clustering algorithm based on obstacle density is proposed, and the nonlinear evaluation function in a high dynamic environment is quickly approximated by Monte Carlo sampling method. Finally, simulations verify the effectiveness of the proposed algorithm in solving dense obstacle avoidance for fixed-wing UAVs.

Towards Fully Autonomous Negative Obstacle Traversal via Imitation Learning Based Control

Current research in experimental robotics has had a focus on traditional, cost-based, navigation methods. These methods ascribe a value of utility for occupying certain locations in the environment. A path planning algorithm then uses this cost function to compute an optimal path relative to obstacle positions based on proximity, visibility, and work efficiency. However, tuning this function to induce more complex navigation behaviors in the robot is not straightforward. For example, this cost-based scheme tends to be pessimistic when assigning traversal cost to negative obstacles. Its often simpler to ascribe high traversal costs to costmap cells based on elevation. This forces the planning algorithm to plan around uneven terrain rather than exploring techniques that understand if and how to safely traverse through them. In this paper, imitation learning is applied to the task of negative obstacle traversal with Unmanned Ground Vehicles (UGVs). Specifically, this work introduces a novel point cloud-based state representation of the local terrain shape and employs imitation learning to train a reactive motion controller for negative obstacle detection and traversal. This method is compared to a classical motion planner that uses the dynamic window approach (DWA) to assign traversal cost based on the terrain slope local to the robots current pose.

Efficient Optimization of Control Libraries

A popular approach to high dimensional control problems in robotics uses a library of candidate “maneuvers” or “trajectories”. The library is either evaluated on a fixed number of candidate choices at runtime (e.g. path set selection for planning) or by iterating through a sequence of feasible choices until success is achieved (e.g. grasp selection). The performance of the library relies heavily on the content and order of the sequence of candidates. We propose a provably efficient method to optimize such libraries, leveraging recent advances in optimizing submodular functions of sequences. This approach is demonstrated on two important problems: mobile robot navigation and manipulator grasp set selection. In the first case, performance can be improved by choosing a subset of candidates which optimizes the metric under consideration (cost of traversal). In the second case, performance can be optimized by minimizing the depth in the list that is searched before a successful candidate is found. Our method can be used in both on-line and batch settings with provable performance guarantees, and can be run in an anytime manner to handle real-time constraints.

Repeated-Task Canadian Traveler Problem

In the Canadian Traveler Problem (CTP) a traveling agent is given a weighted graph, where some of the edges may be blocked, with a known probability. The agent needs to travel to a given goal. A solution for CTP is a policy, that has the smallest expected traversal cost. CTP is intractable. Previous work has focused on the case of a single agent. We generalize CTP to a repeated task version where a number of agents need to travel to the same goal, minimizing their combined travel cost. We provide optimal algorithms for the special case of disjoint path graphs. Based on a previous UCT-based approach for the single agent case, a framework is developed for the multi-agent case and four variants are given - two of which are based on the results for disjoint-path graphs. Empirical results show the benefits of the suggested framework and the resulting heuristics. For small graphs where we could compare to optimal policies, our approach achieves near optimal results at only a fraction of the computation cost.

Speeding Up Reachability Queries in Public Transport Networks Using Graph Partitioning

Computing path queries such as the shortest path in public transport networks is challenging because the path costs between nodes change over time. A reachability query from a node at a given start time on such a network retrieves all points of interest (POIs) that are reachable within a given cost budget. Reachability queries are essential building blocks in many applications, for example, group recommendations, ranking spatial queries, or geomarketing. We propose an efficient solution for reachability queries in public transport networks. Currently, there are two options to solve reachability queries. (1) Execute a modified version of Dijkstra’s algorithm that supports time-dependent edge traversal costs; this solution is slow since it must expand edge by edge and does not use an index. (2) Issue a separate path query for each single POI, i.e., a single reachability query requires answering many path queries. None of these solutions scales to large networks with many POIs. We propose a novel and lightweight reachability index. The key idea is to partition the network into cells. Then, in contrast to other approaches, we expand the network cell by cell. Empirical evaluations on synthetic and real-world networks confirm the efficiency and the effectiveness of our index-based reachability query solution.

FARM: A Flexible Accelerator for Recurrent and Memory Augmented Neural Networks

Recently, Memory Augmented Neural Networks (MANN)s, a class of Deep Neural Networks (DNN)s have become prominent owing to their ability to capture the long term dependencies effectively for several Natural Language Processing (NLP) tasks. These networks augment conventional DNNs by incorporating memory and attention mechanisms external to the network to capture relevant information. Several MANN architectures have shown particular benefits in NLP tasks by augmenting an underlying Recurrent Neural Network (RNN) with external memory using attention mechanisms. Unlike conventional DNNs whose computational time is dominated by MAC operations, MANNs have more diverse behavior. In addition to MACs, the attention mechanisms of MANNs also consist of operations such as similarity measure, sorting, weighted memory access, and pair-wise arithmetic. Due to this greater diversity in operations, MANNs are not trivially accelerated by the same techniques used by existing DNN accelerators. In this work, we present an end-to-end hardware accelerator architecture, FARM, for the inference of RNNs and several variants of MANNs, such as the Differential Neural Computer (DNC), Neural Turing Machine (NTM) and Meta-learning model. FARM achieves an average speedup of 30x-190x and 80x-100x over CPU and GPU implementations, respectively. To address remaining memory bottlenecks in FARM, we then propose the FARM-PIM architecture, which augments FARM with in-memory compute support for MAC and content-similarity operations in order to reduce data traversal costs. FARM-PIM offers an additional speedup of 1.5x compared to FARM. Additionally, we consider an efficiency-oriented version of the PIM implementation, FARM-PIM-LP, that trades a 20% performance reduction relative to FARM for a 4x average power consumption reduction.

Computing Close to Optimal Weighted Shortest Paths in Practice

This paper proposes a new practical method for the weighted region problem (WRP). The objective of WRP is to find a minimum cost path between two vertices among different regions where each region incurs a traversal cost per unit distance. Currently, there is no practical algorithm that solves this problem exactly. Among the approximation methods that solve instances of WRP, there is a limited number of algorithms that compute paths whose lengths are close to optimal, which we call very-close optimum paths. However, they are considered as theoretical methods. On the other hand, algorithms for solving WRP that can be applied to practical data sets (using decomposition ideas or heuristics) are not guaranteed to find a very-close optimum path within an acceptable amount of time. In this paper, we consider an alternative method for solving WRP that exploits Snell's law of physical refraction. We compare the performance of our new algorithm with that of two existing algorithms, using at least 500 test cases for each such comparison. The experimental results show that our algorithm returns a very-close optimum weighted shortest path in reasonable time.

Path-Planning-Enabled Semiflocking Control for Multitarget Monitoring in Mobile Sensor Networks

Mobile sensor networks (MSNs) are good candidates for large-scale unattended surveillance applications. However, it is challenging to track moving targets due to their complex dynamic behaviors. Semiflocking algorithms have been proven to be efficient in controlling MSNs in both area coverage and target tracking applications. While many existing literatures on the study of semiflocking algorithms often assume an area of interest (AoI) to be regular and with unified traversal cost, the uneven and rough landscapes in real-life applications have imposed extra challenges and raised demands for new management strategies. In this article, a mobility map is used to incorporate different costs associated with irregular terrains which results in different maximum allowed speeds on nodes in different regions. In order to reduce target detection time and node energy consumption, a heuristic search algorithm is developed to find time-efficient and feasible paths between nodes and sensing targets. Under the proposed algorithm, nodes can effectively select a target to track or search for new targets in the AoI. Results of extensive experiments show that semiflocking-controlled nodes together with path planning can reach their targets faster with lower energy consumption compared to three exiting flocking-based algorithms.

Parallel Traversal of Large Ensembles of Decision Trees

Machine-learnt models based on additive ensembles of regression trees are currently deemed the best solution to address complex classification, regression, and ranking tasks. The deployment of such models is computationally demanding: to compute the final prediction, the whole ensemble must be traversed by accumulating the contributions of all its trees. In particular, traversal cost impacts applications where the number of candidate items is large, the time budget available to apply the learnt model to them is limited, and the users’ expectations in terms of quality-of-service is high. Document ranking in web search, where sub-optimal ranking models are deployed to find a proper trade-off between efficiency and effectiveness of query answering, is probably the most typical example of this challenging issue. This paper investigates multi/many-core parallelization strategies for speeding up the traversal of large ensembles of regression trees thus obtaining machine-learnt models that are, at the same time, effective, fast, and scalable. Our best results are obtained by the GPU-based parallelization of the state-of-the-art algorithm, with speedups of up to 102.6x.

A Collaborative Stakeholder Decision-Making Approach for Sustainable Urban Logistics

Cities strongly rely on efficient urban logistics to ensure their attractiveness, quality of life, and economic development. In the same time, they strive to ensure livable and safe environments around its road network, where the increased presence of light and heavy goods vehicles raises questions of regarding safety and environmental impacts. Recent literature has well-recognized the need to consider different stakeholders’ perspectives on these issues, in order to achieve desired outcomes. In this paper, we introduce a collaborative stakeholders’ decision-making approach for sustainable urban logistics, and demonstrate its applicability on a real-life example. The suggested approach extends existing route planning approaches by considering route sustainability as a part of an arc’s traversal cost. The integration of route sustainability is based on the adoption of a multi-criterial decision-making approach, with the possibility of including different stakeholders’ points of view, and evaluating the sustainability cost concerning the route’s spatial context. To demonstrate the applicability of the suggested approach, we extract the route sustainability cost from the traffic sign database, and implement the findings on a real-life example. Furthermore, the suggested approach exhibits a high level of transferability to various local contexts, where local stakeholders might have a different view on the route sustainability than is the case in our example.

Complexity of edge coloring with minimum reload/changeover costs

AbstractIn an edge‐colored graph, a traversal cost occurs along a path when consecutive edges with different colors are traversed. The value of the traversal cost depends only on the colors of the edges. Two related global cost measures, namely the reload cost and the changeover cost with applications in telecommunications, transportation networks, and energy distribution networks have been studied in the literature. Previous work focused on problems with an edge‐colored graph being part of the input. In this paper, we formulate problems that aim to find an edge coloring of a graph minimizing the reload and changeover costs. One pair of problems aims to find a proper edge coloring to minimize the reload/changeover cost of a set of paths. Another pair of problems aim to find a proper edge coloring and a spanning tree to minimize the reload/changeover cost. We present several hardness results and polynomial‐time solvable special cases.

Approach to discovering companion patterns based on traffic data stream

A companion of moving objects is an object group that move together in a period of time. Platoon companions are a generalised companion pattern, which describes a group of objects that move together for time segments, each with some minimum consecutive duration of time. This study proposes a method that can instantly discover platoon companions from a special kind of streaming traffic data, called automatic number plate recognition data. Compared to related approaches, the authors transform the companion discovery into a frequent sequence mining problem. The authors propose a data structure, platoon tree (PTree), to record discovered platoon companions. To reduce the cost of tree traversal during mining platoon companions, they utilise the last two together-moving objects of a group to update PTree. Finally, a lot of experiments have been carried out to show the efficiency and effectiveness of the proposed approach.

Path-planning with waiting in spatiotemporally-varying threat fields.

We address the problem of finding an optimal path for a vehicle in a planar environment where traversal costs are based on a time-varying spatial field defined over the environment. The resulting optimal path may contain instances of waiting, where the vehicle hovers, parks, or loiters. First, we consider path-planning on a uniform grid over the workspace. It is known that the computational complexity of the problem is significantly higher when waiting is allowed. We study the trade-off between the increased computational complexity and potential cost reductions in the resultant path with allowance for waiting. The results of numerical studies in this work identify characteristics of the threat fields in which optimal paths can involve waiting. Furthermore, we provide a local condition on the threat field that precludes waiting from providing any cost reductions in the resultant path. We show that this condition can be used in the path-planning algorithm to prune search trees and provide significant reductions in computation time without significant suboptimality. Next, we consider path-planning on a vehicle-centric multiresolution grid. We use a wavelet-based multiresolution decomposition to evaluate the multiresolution path planner and compare against the uniform resolution grid using the same family of threat fields. We show that with a vehicle-centric multiresolution map and an appropriate path-planning algorithm, the added computational effort of allowance for waiting is negligible.