Conditional Generative Models for Dynamic Trajectory Generation and Urban Driving.

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.

Probabilistic Semantic Mapping for Autonomous Driving in Urban Environments.

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.

The neurophysiology of intraoperative error: An EEG study of trainee surgeons during robotic-assisted surgery simulations.

Surgeons operate in mentally and physically demanding workspaces where the impact of error is highly consequential. Accurately characterizing the neurophysiology of surgeons during intraoperative error will help guide more accurate performance assessment and precision training for surgeons and other teleoperators. To better understand the neurophysiology of intraoperative error, we build and deploy a system for intraoperative error detection and electroencephalography (EEG) signal synchronization during robot-assisted surgery (RAS). We then examine the association between EEG data and detected errors. Our results suggest that there are significant EEG changes during intraoperative error that are detectable irrespective of surgical experience level.

Teleoperation for a ball-catching task with significant dynamics.

In this paper we present ongoing work on how to incorporate human motion models into the design of a high performance teleoperation platform. A short description of human motion models used for ball-catching is followed by a more detailed study of a teleoperation platform on which to conduct experiments. Also, a pilot study using minimum jerk theory to explain user input behavior in teleoperated catching is presented.