Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of “what to fuse”, “when to fuse”, and “how to fuse” remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/ .

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system that can be categorized as SAE level 3 or higher. The architecture of the autonomy system of self-driving cars is typically organized into the perception system and the decision-making system. The perception system is generally divided into many subsystems responsible for tasks such as self-driving-car localization, static obstacles mapping, moving obstacles detection and tracking, road mapping, traffic signalization detection and recognition, among others. The decision-making system is commonly partitioned as well into many subsystems responsible for tasks such as route planning, path planning, behavior selection, motion planning, and control. In this survey, we present the typical architecture of the autonomy system of self-driving cars. We also review research on relevant methods for perception and decision making. Furthermore, we present a detailed description of the architecture of the autonomy system of the self-driving car developed at the Universidade Federal do Espirito Santo (UFES), named Intelligent Autonomous Robotics Automobile (IARA). Finally, we list prominent self-driving car research platforms developed by academia and technology companies, and reported in the media.

Self-driving cars: A survey

Autonomous vehicles are expected to play a key role in the future of urban transportation systems, as they offer potential for additional safety, increased productivity, greater accessibility, better road efﬁciency, and positive impact on the environment. Research in autonomous systems has seen dramatic advances in recent years, due to the increases in available computing power and reduced cost in sensing and computing technologies, resulting in maturing technological readiness level of fully autonomous vehicles. The objective of this paper is to provide a general overview of the recent developments in the realm of autonomous vehicle software systems. Fundamental components of autonomous vehicle software are reviewed, and recent developments in each area are discussed.

Perception, Planning, Control, and Coordination for Autonomous Vehicles

This paper presents a systematic review of the perception systems and simulators for autonomous vehicles (AV). This work has been divided into three parts. In the first part, perception systems are categorized as environment perception systems and positioning estimation systems. The paper presents the physical fundamentals, principle functioning, and electromagnetic spectrum used to operate the most common sensors used in perception systems (ultrasonic, RADAR, LiDAR, cameras, IMU, GNSS, RTK, etc.). Furthermore, their strengths and weaknesses are shown, and the quantification of their features using spider charts will allow proper selection of different sensors depending on 11 features. In the second part, the main elements to be taken into account in the simulation of a perception system of an AV are presented. For this purpose, the paper describes simulators for model-based development, the main game engines that can be used for simulation, simulators from the robotics field, and lastly simulators used specifically for AV. Finally, the current state of regulations that are being applied in different countries around the world on issues concerning the implementation of autonomous vehicles is presented.

A systematic review of perception system and simulators for autonomous vehicles research

To assure that an autonomous car is driving safely on public roads, its object detection module should not only work correctly, but show its prediction confidence as well. Previous object detectors driven by deep learning do not explicitly model uncertainties in the neural network. We tackle with this problem by presenting practical methods to capture uncertainties in a 3D vehicle detector for Lidar point clouds. The proposed probabilistic detector represents reliable epistemic uncertainty and aleatoric uncertainty in classification and localization tasks. Experimental results show that the epistemic uncertainty is related to the detection accuracy, whereas the aleatoric uncertainty is influenced by vehicle distance and occlusion. The results also show that we can improve the detection performance by 1%–5% by modeling the aleatoric uncertainty.

Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection

3D Lidar-based static and moving obstacle detection in driving environments

Multimodal vehicle detection: fusing 3D-LIDAR and color camera data

This paper addresses the problem of vehicle detection using Deep Convolutional Neural Network (ConvNet) and 3D-LIDAR data with application in advanced driver assistance systems and autonomous driving. A vehicle detection system based on the Hypothesis Generation (HG) and Verification (HV) paradigms is proposed. The data inputted to the system is a point cloud obtained from a 3D-LIDAR mounted on board an instrumented vehicle, which is transformed to a Dense-depth Map (DM). The proposed solution starts by removing ground points followed by point cloud segmentation. Then, segmented obstacles (object hypotheses) are projected onto the DM. Bounding boxes are fitted to the segmented objects as vehicle hypotheses (the HG step). Finally, the bounding boxes are used as inputs to a ConvNet to classify/verify the hypotheses of belonging to the category ‘vehicle’ (the HV step). In this paper, we present an evaluation of ConvNet using LIDAR-based DMs and also the impact of domain-specific data augmentation on vehicle detection performance. To train and to evaluate the proposed vehicle detection system, the KITTI Benchmark Suite was used.

DepthCN: Vehicle detection using 3D-LIDAR and ConvNet

Object tracking is one of the key components of the perception system of autonomous cars and ADASs. With tracking, an ego-vehicle can make a prediction about the location of surrounding objects in the next time epoch and plan for next actions. Object tracking algorithms typically rely on sensory data (from RGB cameras or LIDAR). In fact, the integration of 2D-RGB camera images and 3D-LIDAR data can provide some distinct benefits. This paper proposes a 3D object tracking algorithm using a 3D-LIDAR, an RGB camera and INS (GPS/IMU) sensors data by analyzing sequential 2D-RGB, 3D point-cloud, and the ego-vehicle's localization data and outputs the trajectory of the tracked object, an estimation of its current velocity, and its predicted location in the 3D world coordinate system in the next time-step. Tracking starts with a known initial 3D bounding box for the object. Two parallel mean-shift algorithms are applied for object detection and localization in the 2D image and 3D point-cloud, followed by a robust 2D/3D Kalman filter based fusion and tracking. Reported results, from both quantitative and qualitative experiments using the KITTI database demonstrate the applicability and efficiency of the proposed approach in driving environments.

3D object tracking using RGB and LIDAR data

High resolution depth-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining data from a monocular camera to compensate the low-resolution of a LIDAR. This paper, on the other hand, introduces a novel framework to obtain dense depth-map solely from a single LIDAR point cloud; which is a research direction that has been barely explored. The formulation behind the proposed depth-mapping process relies on local spatial interpolation, using sliding-window (mask) technique, and on the Bilateral Filter (BF) where the variable of interest, the distance from the sensor, is considered in the interpolation problem. In particular, the BF is conveniently modified to perform depth-map upsampling such that the edges (foreground-background discontinuities) are better preserved by means of a proposed method which influences the range-based weighting term. Other methods for spatial upsampling are discussed, evaluated and compared in terms of different error measures. This paper also researches the role of the mask's size in the performance of the implemented methods. Quantitative and qualitative results from experiments on the KITTI Database, using LIDAR point clouds only, show very satisfactory performance of the approach introduced in this work.

/pdf/high-resolution-lidar-based-depth-mapping-using-bilateral-2u64uarvjb.pdf

Alireza Asvadi

Papers

3D Lidar-based static and moving obstacle detection in driving environments

Multimodal vehicle detection: fusing 3D-LIDAR and color camera data

DepthCN: Vehicle detection using 3D-LIDAR and ConvNet

3D object tracking using RGB and LIDAR data

High-resolution LIDAR-based depth mapping using bilateral filter