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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Predicting the future motion of traffic agents is crucial for safe andefficient autonomous driving. To this end, we present PredictionNet, a deepneural network (DNN) that predicts the motion of all surrounding traffic agentstogether with the ego-vehicle's motion. All predictions are probabilistic andare represented in a simple top-down rasterization that allows an arbitrarynumber of agents. Conditioned on a multi-layer map with lane information, thenetwork outputs future positions, velocities, and backtrace vectors jointly forall agents including the ego-vehicle in a single pass. Trajectories are thenextracted from the output. The network can be used to simulate realistictraffic, and it produces competitive results on popular benchmarks. Moreimportantly, it has been used to successfully control a real-world vehicle forhundreds of kilometers, by combining it with a motion planning/controlsubsystem. The network runs faster than real-time on an embedded GPU, and thesystem shows good generalization (across sensory modalities and locations) dueto the choice of input representation. Furthermore, we demonstrate that byextending the DNN with reinforcement learning (RL), it can better handle rareor unsafe events like aggressive maneuvers and crashes.

PredictionNet: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulation