English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a new scheme to learn motion planning constraints from humandriving trajectories. Behavioral and motion planning are the key components inan autonomous driving system. The behavioral planning is responsible forhigh-level decision making required to follow traffic rules and interact withother road participants. The motion planner role is to generate feasible, safetrajectories for a self-driving vehicle to follow. The trajectories aregenerated through an optimization scheme to optimize a cost function based onmetrics related to smoothness, movability, and comfort, and subject to a set ofconstraints derived from the planned behavior, safety considerations, andfeasibility. A common practice is to manually design the cost function andconstraints. Recent work has investigated learning the cost function from humandriving demonstrations. While effective, the practical application of suchapproaches is still questionable in autonomous driving. In contrast, this paperfocuses on learning driving constraints, which can be used as an add-on moduleto existing autonomous driving solutions. To learn the constraint, the planningproblem is formulated as a constrained Markov Decision Process, whose elementsare assumed to be known except the constraints. The constraints are thenlearned by learning the distribution of expert trajectories and estimating theprobability of optimal trajectories belonging to the learned distribution. Theproposed scheme is evaluated using NGSIM dataset, yielding less than 1\%collision rate and out of road maneuvers when the learned constraints is usedin an optimization-based motion planner.

How To Not Drive: Learning Driving Constraints from Demonstration