Autonomous vehicles have been envisioned for more than 100 years. One of the first suggestions was a front cover of Scientific America back in 1916. Today, it is possible to get cars that drive autonomously for extended distances. We are also starting to see micro-mobility solutions, such as the Nuro vehicles for pizza delivery. Building autonomous cars that can operate in urban environments with a diverse set of road-users is far from trivial. Early 2018 the Contextual Robotics Institute at UC San Diego launched an effort to build a full stack autonomous vehicle for micro-mobility. The motivations were diverse: i) development of a system for operation in an environment with many pedestrians, ii) design of a system that does not rely on dense maps (or HD-maps as they are sometimes named), iii) design strategies to build truly robust systems, and iv) a framework to educate next-generation engineers. In this paper, we present the research effort of design, prototyping, and evaluation of such a vehicle. From the evaluation, several research directions are explored to account for shortcomings. Lessons and issues for future work are additionally drawn from this work.
Statistical learning techniques and increased computational power have facilitated the development of self-driving car technology. However, a limiting factor has been the high expense of scaling and maintaining high-definition (HD) maps. These maps are a crucial backbone for many approaches to self-driving technology. In response to this challenge, we present an approach that fuses pre-built point cloud map data with images to automatically and accurately identify static landmarks such as roads, sidewalks, and crosswalks. Our pipeline utilizes semantic segmentation of 2D images, associates semantic labels with points in point cloud maps to pinpoint locations in the physical world, and employs a confusion matrix formulation to generate a probabilistic bird’s-eye view semantic map from semantic point clouds. The approach has been tested in an urban area with different segmentation networks to generate a semantic map with road features. The resulting map provides a rich context of the environment that is valuable for downstream tasks such as trajectory generation and intent prediction. Moreover, it has the potential to be extended to the automatic generation of HD maps for semantic features. The entire software pipeline is implemented in the robot operating system (ROS), a widely used robotics framework, and made available.
This work explores methodologies for dynamic trajectory generation for urban driving environments by utilizing coarse global plan representations. In contrast to state-of-the-art architectures for autonomous driving that often leverage lane-level high-definition (HD) maps, we focus on minimizing required map priors that are needed to navigate in dynamic environments that may change over time. To incorporate high-level instructions (i.e., turn right vs. turn left at intersections), we compare various representations provided by lightweight and open-source OpenStreetMaps (OSM) and formulate a conditional generative model strategy to explicitly capture the multimodal characteristics of urban driving. To evaluate the performance of the models introduced, a data collection phase is performed using multiple full-scale vehicles with ground truth labels. Our results show potential use cases in dynamic urban driving scenarios with real-time constraints. The dataset is released publicly as part of this work in combination with code and benchmarks.