Modern autonomous systems typically use several sensors for perception. For best performance, accurate and reliable extrinsic calibration is necessary. In this research, we proposea reliable technique for the extrinsic calibration of several lidars on a vehicle without the need for odometry estimation or fiducial markers. First, our method generates an initial guess of the extrinsics by matching the raw signals of IMUs co-located with each lidar. This initial guess is then used in ICP and point cloud feature matching which refines and verifies this estimate. Furthermore, we can use observability criteria to choose a subset of the IMU measurements that have the highest mutual information — rather than comparing all the readings. We have successfully validated our methodology using data gathered from Scania test vehicles.

Modern autonomous systems typically use several sensors for perception. For best performance, accurate and reliable extrinsic calibration is necessary. In this research, we propose a reliable technique for the extrinsic calibration of several lidars on a vehicle without the need for odometry estimation or fiducial markers. First, our method generates an initial guess of the extrinsics by matching the raw signals of IMUs co-located with each lidar. This initial guess is then used in ICP and point cloud feature matching which refines and verifies this estimate. Furthermore, we can use observability criteria to choose a subset of the IMU measurements that have the highest mutual information - rather than comparing all the readings. We have successfully validated our methodology using data gathered from Scania test vehicles.

Localization and mapping is one of the key aspects of driving autonomously in unstructured environments. Often such vehicles are equipped with multiple sensor modalities to create a 360^o sensing coverage and add redundancy to handle sensor dropout scenarios. As the vehicles operate in underground mining and dense urban environments the Global navigation satellite system (GNSS) is often unreliable. Hence, to create a robust localization system different sensor modalities like camera, lidar and IMU are used along with a GNSS solution. The system must handle sensor dropouts and work in real-time (~15 Hz), so that there is enough computation budget left for other tasks like planning and control. Additionally, precise localization is also needed to map the environment, which may be later used for re-localization of the autonomous vehicles as well. Finally, for all of these to work seamlessly, accurate calibration of the sensors is of utmost importance.

In this PhD thesis, first, a robust system for state estimation that fuses measurements from multiple lidars and inertial sensors with GNSS data is presented. State estimation was performed in real-time, which produced robust motion estimates in a global frame by fusing lidar and IMU signals with GNSS components using a factor graph framework. The proposed method handled signal loss with a novel synchronization and fusion mechanism. To validate the approach extensive tests were carried out on data collected using Scania test vehicles (5 sequences for a total of ~ 7 Km). An average improvement of 61% in relative translation and 42% rotational error compared to a state-of-the-art estimator fusing a single lidar/inertial sensor pair is reported.  

Since precise calibration is needed for the localization and mapping tasks, in this thesis, methods for real-time calibration of the sensor setup is proposed. First, a method is proposed to calibrate sensors with non-overlapping field-of-view. The calibration quality is verified by mapping known features in the environment. Nevertheless, the verification process was not real-time and no observability analysis was performed which could give us an indicator of the analytical traceability of the trajectory required for motion-based online calibration. Hence, a new method is proposed where calibration and verification were performed in real-time by matching estimated sensor poses in real-time with observability analysis. Both of these methods relied on estimating the sensor poses using the state estimator developed in our earlier works. However, state estimators have inherent drifts and they are computationally intensive as well. Thus, another novel method is developed where the sensors could be calibrated in real-time without the need for any state estimation. 

We present a robust system for state estimation that fuses measurements from multiple lidars and inertial sensors with GNSS data. To initiate the method, we use the prior GNSS pose information. We then perform motion estimation in real-time, which produces robust motion estimates in a global frame by fusing lidar and IMU signals with GNSS translation components using a factor graph framework. We also propose methods to account for signal loss with a novel synchronization and fusion mechanism. To validate our approach extensive tests were carried out on data collected using Scania test vehicles (5 sequences for a total of ≈ 7 Km). From our evaluations, we show an average improvement of 61% in relative translation and 42% rotational error compared to a state-of-the-art estimator fusing a single lidar/inertial sensor pair, in sensor dropout scenarios.

Accurate and robust extrinsic calibration is necessary for deploying autonomous systems which need multiple sensors for perception. In this letter, we present a robust system for real-time extrinsic calibration of multiple lidars in vehicle base framewithout the need for any fiducialmarkers or features. We base our approach on matching absolute GNSS (Global Navigation Satellite System) and estimated lidar poses in real-time. Comparing rotation components allows us to improve the robustness of the solution than traditional least-square approach comparing translation components only. Additionally, instead of comparing all corresponding poses, we select poses comprising maximum mutual information based on our novel observability criteria. This allows us to identify a subset of the poses helpful for real-time calibration. We also provide stopping criteria for ensuring calibration completion. To validate our approach extensive tests were carried out on data collected using Scania test vehicles (7 sequences for a total of approximate to 6.5 Km). The results presented in this letter show that our approach is able to accurately determine the extrinsic calibration for various combinations of sensor setups.

We demonstrate a multi-lidar calibration framework for large mobile platforms that jointly calibrate the extrinsic parameters of non-overlapping Field-of-View (FoV) lidar sensors, without the need for any external calibration aid. The method starts by estimating the pose of each lidar in its corresponding sensor frame in between subsequent timestamps. Since the pose estimates from the lidars are not necessarily synchronous, we first align the poses using a Dual Quaternion (DQ) based Screw Linear Interpolation. Afterward, a HandEye based calibration problem is solved using the DQ-based formulation to recover the extrinsics. Furthermore, we verify the extrinsics by matching chosen lidar semantic features, obtained by projecting the lidar data into the camera perspective after time alignment using vehicle kinematics. Experimental results on the data collected from a Scania vehicle [similar to 1 Km sequence] demonstrate the ability of our approach to obtain better calibration parameters than the provided vehicle CAD model calibration parameters. This setup can also be scaled to any combination of multiple lidars.

Reliable knowledge of road boundaries is critical for autonomous vehicle navigation. We propose a robust curb detection and filtering technique based on the fusion of camera semantics and dense lidar point clouds. The lidar point clouds are collected by fusing multiple lidars for robust feature detection. The camera semantics are based on a modified EfficientNet architecture which is trained with labeled data collected from onboard fisheye cameras. The point clouds are associated with the closest curb segment with L2-norm analysis after projecting into the image space with the fisheye model projection. Next, the selected points are clustered using unsupervised density-based spatial clustering to detect different curb regions. As new curb points are detected in consecutive frames they are associated with the existing curb clusters using temporal reachability constraints. If no reachability constraints are found a new curb cluster is formed from these new points. This ensures we can detect multiple curbs present in road segments consisting of multiple lanes if they are in the sensors' field of view. Finally, Delaunay filtering is applied for outlier removal and its performance is compared to traditional RANSAC-based filtering. An objective evaluation of the proposed solution is done using a high-definition map containing ground truth curb points obtained from a commercial map supplier. The proposed system has proven capable of detecting curbs of any orientation in complex urban road scenarios comprising straight roads, curved roads, and intersections with traffic isles. 

We propose a greedy algorithm to select N important features among P input features for a non-linear prediction problem. The features are selected one by one sequentially, in an iterative loss minimization procedure. We use neural networks as predictors in the algorithm to compute the loss and hence, we refer to our method as neural greedy pursuit (NGP). NGP is efficient in selecting N features when N << P, and it provides a notion of feature importance in a descending order following the sequential selection procedure. We experimentally show that NGP provides better performance than several feature selection methods such as DeepLIFT and Drop-one-out loss. In addition, we experimentally show a phase transition behavior in which perfect selection of all N features without false positives is possible when the training data size exceeds a threshold.

We propose ReDense as a simple and low complexity way to improve the performance of trained neural networks. We use a combination of random weights and rectified linear unit (ReLU) activation function to add a ReLU dense (ReDense) layer to the trained neural network such that it can achieve a lower training loss. The lossless flow property (LFP) of ReLU is the key to achieve the lower training loss while keeping the generalization error small. ReDense does not suffer from vanishing gradient problem in the training due to having a shallow structure. We experimentally show that ReDense can improve the training and testing performance of various neural network architectures with different optimization loss and activation functions. Finally, we test ReDense on some of the state-of-the-art architectures and show the performance improvement on benchmark.

We present an efficient multi-sensor odometry system for mobile platforms that jointly optimizes visual, lidar, and inertial information within a single integrated factor graph. This runs in real-time at full framerate using fixed lag smoothing. To perform such tight integration, a new method to extract 3D line and planar primitives from lidar point clouds is presented. This approach overcomes the suboptimality of typical frame-to-frame tracking methods by treating the primitives as landmarks and tracking them over multiple scans. True integration of lidar features with standard visual features and IMU is made possible using a subtle passive synchronization of lidar and camera frames. The lightweight formulation of the 3D features allows for real-time execution on a single CPU. Our proposed system has been tested on a variety of platforms and scenarios, including underground exploration with a legged robot and outdoor scanning with a dynamically moving handheld device, for a total duration of 96 min and 2.4 km traveled distance. In these test sequences, using only one exteroceptive sensor leads to failure due to either underconstrained geometry (affecting lidar) or textureless areas caused by aggressive lighting changes (affecting vision). In these conditions, our factor graph naturally uses the best information available from each sensor modality without any hard switches.