# Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models

Source: [Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models](<https://www.sota2.com/research/paper/68fa62181e209131ce9f78d9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:12:29.814Z

Authors: Ashesh Jain, Hema S. Koppula, Bharad Raghavan, Shane Soh, Ashutosh Saxena

Published: 2015-04-10T20:52:40.000Z

## Abstract

Advanced Driver Assistance Systems (ADAS) have made driving safer over the last decade. They prepare vehicles for unsafe road conditions and alert drivers if they perform a dangerous maneuver. However, many accidents are unavoidable because by the time drivers are alerted, it is already too late. Anticipating maneuvers beforehand can alert drivers before they perform the maneuver and also give ADAS more time to avoid or prepare for the danger.   In this work we anticipate driving maneuvers a few seconds before they occur. For this purpose we equip a car with cameras and a computing device to capture the driving context from both inside and outside of the car. We propose an Autoregressive Input-Output HMM to model the contextual information alongwith the maneuvers. We evaluate our approach on a diverse data set with 1180 miles of natural freeway and city driving and show that we can anticipate maneuvers 3.5 seconds before they occur with over 80\\% F1-score in real-time.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Maneuver Anticipation on 1100 miles of real-world driving data (Turns)](<https://www.sota2.com/research/sota/maneuver-anticipation-on-1100-miles-of-real-world-driving-data-turns.md>): Maneuver Anticipation; 1100 miles of real-world driving data (Turns); Precision: 80.8.

- [Maneuver Anticipation on 1100 miles of real-world driving data (Lane change)](<https://www.sota2.com/research/sota/maneuver-anticipation-on-1100-miles-of-real-world-driving-data-lane-change.md>): Maneuver Anticipation; 1100 miles of real-world driving data (Lane change); Precision: 83.8.

- [Maneuver Anticipation on 1100 miles of real-world driving data (All maneuvers)](<https://www.sota2.com/research/sota/maneuver-anticipation-on-1100-miles-of-real-world-driving-data-all-maneuvers.md>): Maneuver Anticipation; 1100 miles of real-world driving data (All maneuvers); Precision: 77.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1504.02789>)

[PDF](<https://arxiv.org/pdf/1504.02789.pdf>)