MP3: A Unified Model to Map, Perceive, Predict and Plan

01/18/2021
by   Sergio Casas, et al.
14

High-definition maps (HD maps) are a key component of most modern self-driving systems due to their valuable semantic and geometric information. Unfortunately, building HD maps has proven hard to scale due to their cost as well as the requirements they impose in the localization system that has to work everywhere with centimeter-level accuracy. Being able to drive without an HD map would be very beneficial to scale self-driving solutions as well as to increase the failure tolerance of existing ones (e.g., if localization fails or the map is not up-to-date). Towards this goal, we propose MP3, an end-to-end approach to mapless driving where the input is raw sensor data and a high-level command (e.g., turn left at the intersection). MP3 predicts intermediate representations in the form of an online map and the current and future state of dynamic agents, and exploits them in a novel neural motion planner to make interpretable decisions taking into account uncertainty. We show that our approach is significantly safer, more comfortable, and can follow commands better than the baselines in challenging long-term closed-loop simulations, as well as when compared to an expert driver in a large-scale real-world dataset.

READ FULL TEXT

page 4

page 16

page 17

page 18

page 19

research
01/17/2021

End-to-end Interpretable Neural Motion Planner

In this paper, we propose a neural motion planner (NMP) for learning to ...
research
08/13/2020

Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations

In this paper we propose a novel end-to-end learnable network that perfo...
research
01/16/2021

LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving

Self-driving vehicles need to anticipate a diverse set of future traffic...
research
01/20/2021

IntentNet: Learning to Predict Intention from Raw Sensor Data

In order to plan a safe maneuver, self-driving vehicles need to understa...
research
06/08/2023

UAP-BEV: Uncertainty Aware Planning using Bird's Eye View generated from Surround Monocular Images

Autonomous driving requires accurate reasoning of the location of object...
research
07/01/2022

MMFN: Multi-Modal-Fusion-Net for End-to-End Driving

Inspired by the fact that humans use diverse sensory organs to perceive ...
research
03/03/2022

Quantity over Quality: Training an AV Motion Planner with Large Scale Commodity Vision Data

With the Autonomous Vehicle (AV) industry shifting towards Autonomy 2.0,...

Please sign up or login with your details

Forgot password? Click here to reset