Within the context of autonomous driving, safetyrelated metrics for deep neural networks have been widely studied for image classification and object detection. In this paper, we further consider safety-aware correctness and robustness metrics specialized for semantic segmentation. The novelty of our proposal is to move beyond pixel-level metrics: Given two images with each having n pixels being class-flipped, the designed metrics should, depending on the clustering of pixels being class-flipped or the location of occurrence, reflect a different level of safety criticality. The result evaluated on an autonomous driving dataset demonstrates the validity and practicality of our proposed methodology.
The time-optimal control problem (TOCP) has faced new practical challenges, such as those from the deployment of agile autonomous vehicles in diverse uncertain operating conditions without accurate system calibration. In this study to meet a need to generate feasible speed profiles in the face of uncertainty, we exploit and implement probabilistic inference for learning control (PILCO), an existing sample-efficient model-based reinforcement learning (MBRL) framework for policy search, to a case study of TOCP for a vehicle that was modeled as a constant input-constrained double integrator with uncertain inertia subject to uncertain viscous friction. Our approach integrates learning, planning, and control to construct a generalizable approach that requires minimal assumptions (especially regarding external disturbances and the parametric dynamics model of the system) for solving TOCP approximately as the perturbed solutions close to time-optimality. Within PILCO, a Gaussian Radial basis functions is implemented to generate control-constrained rest-to-rest near time-optimal vehicle motion on a linear track from scratch with data-efficiency in a direct way. We briefly introduce the importance of the applications of PILCO and discuss the learning results that PILCO would actually converge to the analytical solution in this TOCP. Furthermore, we execute a simulation and a sim2real experiment to validate the suitability of PILCO for TOCP by comparing with the analytical solution.
An autonomous robot typically requires a minimum capability of perceiving the surroundings and locating itself when it is deployed to an unknown environment. Such a task is generally known as Simultaneous Localization and Mapping (SLAM), for which pairwise submap matching is a common foundation for subsequent processes to construct a global map around the robot. While the task has been extensively studied and successfully accomplished with different advanced solutions, their applied domains are rather constrained within indoor or structured regions. In this paper, we enhance a seminal learning-based approach, 3DFeat-Net, with more sophisticated architectures, and evaluate them in extremely unorganized planetary-like environments. Our work demonstrates that the proposed enhancement performs better than classical feature-based algorithms, and therefore outlines a promising direction for future work.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.