Being able to anticipate the motion of surrounding agents is essential for the safe operation of autonomous driving systems in dynamic situations. While various methods have been proposed for trajectory prediction, the current evaluation practices still rely on error-based metrics (e.g., ADE, FDE), which reveal the accuracy from a post-hoc view but ignore the actual effect the predictor brings to the self-driving vehicles (SDVs), especially in complex interactive scenarios: a high-quality predictor not only chases accuracy, but should also captures all possible directions a neighbor agent might move, to support the SDVs' cautious decision-making. Given that the existing metrics hardly account for this standard, in our work, we propose a comprehensive pipeline that adaptively evaluates the predictor's performance by two dimensions: accuracy and diversity. Based on the criticality of the driving scenario, these two dimensions are dynamically combined and result in a final score for the predictor's performance. Extensive experiments on a closed-loop benchmark using a real-world dataset show that our pipeline yields a more reasonable evaluation than traditional metrics by better reflecting the correlation of the predictors' evaluation with the autonomous vehicles' driving performance. This evaluation pipeline shows a robust way to select a predictor that potentially contributes most to the SDV's driving performance.

Smooth and safe speed planning is imperative for the successful deployment of autonomous vehicles. This paper presents a mathematical formulation for the optimal speed planning of autonomous driving, which has been validated in high-fidelity simulations and real-road demonstrations with practical constraints. The algorithm explores the inter-traffic gaps in the time and space domain using a breadth-first search. For each gap, quadratic programming finds an optimal speed profile, synchronizing the time and space pair along with dynamic obstacles. Qualitative and quantitative analysis in Carla is reported to discuss the smoothness and robustness of the proposed algorithm. Finally, we present a road demonstration result for urban city driving.

Robotic exploration requires adaptively selecting navigation goals that result in the rapid discovery and mapping of an unknown world. In many real-world environments, subtle structural cues can provide insight about the unexplored world, which may be exploited by a decision maker to improve the speed of exploration. In sparse subterranean tunnel networks, these cues come in the form of topological features, such as loops or dead-ends, that are often common across similar environments. We propose a method for learning these topological features using techniques borrowed from topological image segmentation and image inpainting to learn from a database of worlds. These world predictions then inform a frontier-based exploration policy. Our simulated experiments with a set of real-world mine environments and a database of procedurally-generated artificial tunnel networks demonstrate a substantial increase in the rate of area explored compared to techniques that do not attempt to predict and exploit topological features of the unexplored world.