5 January 2023 in Journal of Field Robotics
13 April 2022 in IEEE Transactions on Intelligent Transportation Systems
Most of the recent automated driving systems assume the accurate functioning of localization. Unanticipated errors cause localization failures and result in failures in automated driving. An exact localization failure detection is necessary to ensure safety in automated driving; however, detection of the localization failures is challenging because sensor measurement is assumed to be independent of each other in the localization process. Owing to the assumption, the entire relation of the sensor measurement is ignored. Consequently, it is difficult to recognize the misalignment between the sensor measurement and the map when partial sensor measurement overlaps with the map. This paper proposes a method for the detection of localization failures using Markov random fields with fully connected latent variables. The full connection enables to take the entire relation into account and contributes to the exact misalignment recognition. Additionally, this paper presents localization failure probability calculation and efficient distance field representation methods. We evaluate the proposed method using two types of datasets. The first dataset is the SemanticKITTI dataset, whereby four methods are compared with the proposed method. The comparison results reveal that the proposed method achieves the most accurate failure detection. The second dataset is created based on log data acquired from the demonstrations that we conducted in Japanese public roads. The dataset includes several localization failure scenes. We apply the failure detection methods to the dataset and confirm that the proposed method achieves exact and immediate failure detection.
22 July 2019 in IEEE Robotics and Automation Letters
Recognizing misalignment between sensor measurements and objects that exist on a map due to inaccuracies in localization estimation is challenging. This can be attributed to the fact that the sensor measurements are individually modeled for solving the localization problem, resulting in entire relations of the measurements being ignored. This letter proposes a misalignment recognition method using Markov random fields with fully connected latent variables for the detection of localization failures. The proposed method estimates the classes of each sensor measurement that are aligned, misaligned, and obtained from unknown obstacles. The full connection allows us to consider the entire relation of the measurements. A misalignment can be exactly recognized even when partial sensor measurements overlap with mapped objects. Based on the class estimation results, we are able to distinguish whether the localization has failed or not. The proposed method was compared with six alternative methods, including a convolutional neural network, using datasets composed of success and failure localization samples. Experimental results show that the classification accuracy of the localization samples using the proposed method exceeds 95% and outperforms the other examined methods.
28 May 2020 in IEEE Robotics and Automation Letters
Semantics can be leveraged in ego-vehicle localization to improve robustness and accuracy because objects with the same labels can be correctly matched with each other. Object recognition has significantly improved owing to advances in machine learning algorithms. However, perfect object recognition is still challenging in real environments. Hence, the uncertainty of object recognition must be considered in localization. This paper proposes a novel localization method that integrates a supervised object recognition method, which predicts probabilistic distributions over object classes for individual sensor measurements, into the Bayesian network for localization. The proposed method uses the estimated probabilities and Dirichlet distribution to calculate the likelihood for estimating an ego-vehicle pose. Consequently, the uncertainty can be handled in localization. We present an implementation example of the proposed method using a particle filter and deep-neural-network-based point cloud semantic segmentation and evaluate it by simulation and the SemanticKITTI dataset. Experimental results show that the proposed method can accurately generate likelihood distribution even when object recognition accuracy is degraded, and its estimation accuracy is the highest compared to that of two conventional methods.