Computing occupancy grids from multiple sensors using linear opinion pools

We introduce an alternative to the popular linear opinion pool for combining individual probability forecasts. One of the well-known problems with the linear opinion pool is that it can be poorly calibrated. It tends toward underconfidence as the crowd's diversity increases, i.e., as the variance in the individuals' means increases. To address this calibration problem, we propose the exterior-trimmed opinion pool. To form this pool, forecasts with low and high means, or cumulative distribution function (cdf) values, are trimmed away from a linear opinion pool. Exterior trimming decreases the pool's variance and improves its calibration. A linear opinion pool, however, will remain overconfident when individuals are overconfident and not very diverse. For these situations, we suggest trimming away forecasts with moderate means or cdf values. This interior trimming increases variance and reduces overconfidence. Using probability forecast data from U.S. and European Surveys of Professional Forecasters, we present empirical evidence that trimmed opinion pools can outperform the linear opinion pool.This paper was accepted by Rakesh Sarin, decision analysis.

Occupancy grid state mapping is a key process in robotics and autonomous driving systems. It divides the environment into grid cells that contain information states. In this paper, we propose a modified SMC-BOF method to map and predict occupancy grids. The original SMC-BOF has been widely used in the occupancy grid mapping because it has lower computational costs than the BOF method. However, there are some issues related to conflicting information in dynamic situations. The original SMC-BOF cannot completely control an elongated vehicle that has conflicting information caused by the height difference between backward of vehicle and ground. To overcome this problem, we add confidence weights onto a part of the grid mapping process of the original SMC-BOF using the Linear Opinion Pool. We evaluate our method by LIDAR and stereo vision data in the KITTI dataset.

Trading in information markets, such as machine learning markets, has been shown to be an effective approach for aggregating the beliefs of different agents. In a machine learning context, aggregation commonly uses forms of linear opinion pools, or logarithmic (log) opinion pools. It is interesting to relate information market aggregation to the machine learning setting. In this paper we introduce a spectrum of compositional methods, Renyi divergence aggregators, that interpolate between log opinion pools and linear opinion pools. We show that these compositional methods are maximum entropy distributions for aggregating information from agents subject to individual biases, with the Renyi divergence parameter dependent on the bias. In the limit of no bias this reduces to the optimal limit of log opinion pools. We demonstrate this relationship practically on both simulated and real datasets. We then return to information markets and show that Renyi divergence aggregators are directly implemented by machine learning markets with isoelastic utilities, and so can result from autonomous self interested decision making by individuals contributing different predictors. The risk averseness of the isoelastic utility directly relates to the Renyi divergence parameter, and hence encodes how much an agent believes (s)he may be subject to an individual bias that could affect the trading outcome: if an agent believes (s)he might be acting on significantly biased information, a more risk averse isoelastic utility is warranted.

For the last 25 years, occupancy grids have been intensively used as a well-understood framework for many robotic applications, such as path planning or obstacle avoidance. They offer a unifying framework for multiple heterogeneous sensor integration using a probabilistic representation of sensor data. This integration is computed through Bayesian techniques or evidence combination approaches, both requiring high computation workload using real number representation. In critical application domains, it is challenging to fuse data coming out of several sensors in real-time using constrained embedded platforms. In this paper, we propose a revised theoretical formulation of multi-sensor fusion using only integer arithmetic. We apply this novel framework to compute occupancy grid by only using integer numbers to represent probabilities. Compared to the state-of-the-art solutions, our fusion framework enables implementation on platforms with no floating-point support. Our experiments demonstrate that fusion of real automotive data from a 4-scans LIDAR can be integrated into a microcontroller without a floating-point unit. Our approach opens the perspective for microcontroller or even for hardware block based on ASIC or FPGA to support occupancy grid applications with real-time performance.

In terms of navigation, a central problem in the field of autonomous robotics is obstacle avoidance. This research explores how to navigate as well as avoid obstacles by leveraging what is known of the environment to determine decisions with new incoming information during execution. The algorithm presented in this work is divided into two procedures: an offline process that uses prior knowledge to navigate toward the goal; and an online execution strategy that leverages results obtained offline to drive safely towards the target when new information is encountered (e.g., obstacles). To take advantage of what is known offline, the navigation problem was formulated as a Markov Decision Process (MDP) where the environment is characterized as an occupancy grid. Baseline dynamic programming techniques were used to solve this, producing general behaviors that drive the robot (or agent) toward the goal and a value function which encodes the value of being in particular states. Then during online execution, the agent uses these offline results and surrounding local information of the environment to operate (e.g., data from a LIDAR sensor). This locally acquired information, which may contain new data not seen prior, is represented as a small occupancy grid and leverages the offline obtained value function to define local goals allowing the agent to make short term plans. When the agent encounters an obstacle locally, the problem becomes a Partially Observable Markov Decision Process (POMDP) since it is uncertain where these obstacles will be in the next state. This is solved by utilizing an approximate planner (QMDP) that uses uncertainty of the obstacle motion and considers all possible obstacle state combinations in the next time step to determine the best action. The approximate planner can quickly solve the POMDP, due to the small size of the local occupancy grid and by using the behaviors produced offline to help speed up convergence, which opens the possibility for this procedure to be executed in real time, on a physical robot. Two simulated environments were created, varying in complexity and dynamic obstacles. Simulation results under complex conditions with narrow operable spaces and many dynamic obstacles show the proposed algorithm has approximately an 85% success rate, in test cases with cluttered environments and multiple dynamic obstacles, and is shown to produce safer trajectories than the baseline approach, which had roughly a 37% success rate, under the assumptions that dynamic obstacles can only move a short distance by

Most existing expert systems contain a single rule base. Any extension of this model to group decision-making must account for the possibility of conflicting rules encoded by different group members. The inability to reconcile conflicts, however, is one of the most clearly established shortcomings of rule-based knowledge representations [4] [11]. Thus, multi-expert rule-bases are likely to be inelegant and confusing at best, incorrect and useless at worst. The creation of advisory systems whose recommendations are based on the input of multiple experts, then, calls for an alternative knowledge representation.

In the absence of long-term data, structured expert elicitation gathers expert judgments and associated uncertainties to assess the clinical plausibility of long-term extrapolations. The objective of this study was to obtain expert estimates of expected long-term outcomes for advanced renal cell carcinoma treatments to inform cost-effectiveness analysis for National Institute for Health and Care Excellence (NICE)'s pathways pilot. Using materials from the structured expert elicitation resources (STEER) repository, aligned with the Medical Research Council (MRC) protocol, the exercise was planned and conducted. Aiming for 5-10 oncologists from diverse UK geographies and settings, experts estimated progression-free survival (PFS) at three landmark timepoints for 21 disease-risk-prior treatment combinations and overall survival for best supportive care. Within an 8-week timeframe, we piloted with one clinician, conducted online training, collected responses via an online survey using the roulette method and mathematically aggregated results through linear opinion pooling. Nine experts participated (question response rate: 95%). For first-line intermediate/poor-risk patients, clinicians projected similar PFS for three immune oncology/tyrosinekinase inhibitor (TKI) combinations from 5years onward and comparable PFS for two TKI monotherapies. Nivolumab+ipilimumab was anticipated to achieve the highest PFS amongst first-line therapies. Expert reasoning incorporated treatment class, clinical experience, and awareness of trial data optimism. Expert estimates were generally somewhat optimistic compared with observed UK real-world evidence and pessimistic compared with observed trial data. Structured expert elicitation is a pragmatic, efficient approach for informing long-term survival extrapolations in the context of a rapidly evolving treatment pathway. We demonstrated that expert elicitation is possible even for complex decision problems in a relatively short timeframe.

Terms-based discriminative information space for robust text classification

Abstract. LIDAR sensors are widely used in mobile mapping systems. The mobile mapping platforms allow to have fast acquisition in cities for example, which would take much longer with static mapping systems. The LIDAR sensors provide reliable and precise 3D information, which can be used in various applications: mapping of the environment; localization of objects; detection of changes. Also, with the recent developments, multi-beam LIDAR sensors have appeared, and are able to provide a high amount of data with a high level of detail. A mono-beam LIDAR sensor mounted on a mobile platform will have an extrinsic calibration to be done, so the data acquired and registered in the sensor reference frame can be represented in the body reference frame, modeling the mobile system. For a multibeam LIDAR sensor, we can separate its calibration into two distinct parts: on one hand, we have an extrinsic calibration, in common with mono-beam LIDAR sensors, which gives the transformation between the sensor cartesian reference frame and the body reference frame. On the other hand, there is an intrinsic calibration, which gives the relations between the beams of the multi-beam sensor. This calibration depends on a model given by the constructor, but the model can be non optimal, which would bring errors and noise into the acquired point clouds. In the litterature, some optimizations of the calibration parameters are proposed, but need a specific routine or environment, which can be constraining and time-consuming. In this article, we present an automatic method for improving the intrinsic calibration of a multi-beam LIDAR sensor, the Velodyne HDL-32E. The proposed approach does not need any calibration target, and only uses information from the acquired point clouds, which makes it simple and fast to use. Also, a corrected model for the Velodyne sensor is proposed. An energy function which penalizes points far from local planar surfaces is used to optimize the different proposed parameters for the corrected model, and we are able to give a confidence value for the calibration parameters found. Optimization results on both synthetic and real data are presented.

Using spatiotemporal stacks for precise vehicle tracking from roadside 3D LiDAR data

This paper presents a Lidar-based multiple-sensor system that is used to estimate the motion of the observer via surrounding information. As a basic solution for surrounding sensing, SLAM is a system that combines simultaneous localization and mapping. It supports several types of sensors, including Lidar sensor, camera, odometer, and IMU (Inertial Measurement Unit). We focus on applying the SLAM system to a multiple linear laser Lidar sensor group by using only their sensing data stream of length and angle. For this sensor group, we propose a new method that combines an image phase correlation algorithm and pose-graph optimized algorithm to implement obstacles detection and motion estimation. We also design a filter applying the combination method to the Lidar sensor.

Depth sensing is critical to many computer vision applications but remains challenge to generate accurate dense information with single type sensor. The stereo camera sensor can provide dense depth prediction but underperforms in texture-less, repetitive and occlusion areas while the LiDAR sensor can generate accurate measurements but results in sparse map. In this paper, we advocate to fuse LiDAR and stereo camera for accurate dense depth sensing. We consider the fusion of multiple sensors as a multimodal prediction problem. We propose a novel end-to-end learning framework, dubbed as LSMD-Net to faithfully generate dense depth. The proposed method has dual-branch disparity predictor and predicts a bimodal Laplacian distribution over disparity at each pixel. This distribution has two modes which captures the information from two branches. Predictions from the branch with higher confidence is selected as the final disparity result at each specific pixel. Our fusion method can be applied for different type of LiDARs. Besides the existing dataset captured by conventional spinning LiDAR, we build a multiple sensor system with a non-repeating scanning LiDAR and a stereo camera and construct a depth prediction dataset with this system. Evaluations on both KITTI datasets and our home-made dataset demonstrate the superiority of our proposed method in terms of accuracy and computation time.

In this paper we propose a robust curb detection method which is based on the fusion between semantically labeled camera images and a 3D point cloud coming from LiDAR sensors. The labels from the semantically enhanced cloud are used to reduce the curbs’ searching area. Several spatial cues are next computed on each candidate curb region. Based on these features, a candidate curb region is either rejected or refined for obtaining a precise positioning of the curb points found inside it. A novel local model-based outlier removal algorithm is proposed to filter out the erroneous curb points. Finally, a temporal integration of the detected curb points in multiple consecutive frames is used to densify the detection result. An objective evaluation of the proposed solution is done using a high-resolution digital map containing ground truth curb points. The proposed system has proved capable of detecting curbs of any heights (from 3cm up to 30cm) in complex urban road scenarios (straight roads, curved roads, intersections with traffic isles and roundabouts).

Abstract. 3D LiDAR sensors play an important part in several autonomous navigation and perception systems with the technology evolving rapidly over time. This work presents the preliminary evaluation results of a 3D solid state LiDAR sensor. Different aspects of this new type of sensor are studied and their data are characterized for their effective utilization for object detection for the application of Autonomous Ground Vehicles (AGV). The paper provides a set of evaluations to analyze the characterizations and performances of such LiDAR sensors. After characterization of the sensor, the performance is also evaluated in real environment with the sensors mounted on top of a vehicle and used to detect and classify different objects using a state-of-the-art Super-Voxel based method. The 3D point cloud obtained from the sensor is classified into three main object classes “Building”, “Ground” and “Obstacles”. The results evaluated on real data, clearly demonstrate the applicability and suitability of the sensor for such type of applications.

Autonomous vehicles and mobile edge computing’s confluence have raised an innovative model for immediate decision-making and improved computational abilities. But, enhancing vehicle management systems to guarantee effective enactment remains an important challenge. Present approaches regularly depend on intricate algorithms and multiple sensors, that result in improved computational overhead and potential latency. The current study resolves the present gap by offering a new hybrid framework, which synergistically mixes optimization algorithms and deep neural networks through the advantages of mobile edge computing. Precisely, this research presents a hybrid model for autonomous vehicle management by integrating a refined version of the RPO or Pelican Optimizer with deep neural networks attuned to mobile edge computing environments. The chief contributions of the present study have been threefold: (1) the improvement of a particular autonomous driving method optimized for mobile edge computing platforms; (2) the arrangement of an optimized MobileNet method employing the RPO algorithm that uses LiDAR sensor data for effective object recognition and path design; and (3) the construction of an indoor vehicle prototype by mean of a microcontroller and LiDAR sensors, after a comprehensive performance evaluation of inference models, and analyzing the trade-offs between input size and computational effectiveness. Experimental outcomes show the efficiency and reliability of the suggested hybrid model, through improving autonomous vehicle management and decision-making abilities within the mobile edge computing paradigm. The current study contributes to the enhancement of autonomous vehicle research and provides an innovative solution for effective and precise vehicle control within edge computing environments.