Vehicle trajectory prediction works, but not everywhere
- URL: http://arxiv.org/abs/2112.03909v1
- Date: Tue, 7 Dec 2021 18:59:15 GMT
- Title: Vehicle trajectory prediction works, but not everywhere
- Authors: Mohammadhossein Bahari, Saeed Saadatnejad, Ahmad Rahimi, Mohammad
Shaverdikondori, Mohammad Shahidzadeh, Seyed-Mohsen Moosavi-Dezfooli,
Alexandre Alahi
- Abstract summary: We present a novel method that automatically generates realistic scenes that cause state-of-the-art models go off-road.
We promote a simple yet effective generative model based on atomic scene generation functions along with physical constraints.
- Score: 75.36961426916639
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Vehicle trajectory prediction is nowadays a fundamental pillar of
self-driving cars. Both the industry and research communities have acknowledged
the need for such a pillar by running public benchmarks. While state-of-the-art
methods are impressive, i.e., they have no off-road prediction, their
generalization to cities outside of the benchmark is unknown. In this work, we
show that those methods do not generalize to new scenes. We present a novel
method that automatically generates realistic scenes that cause
state-of-the-art models go off-road. We frame the problem through the lens of
adversarial scene generation. We promote a simple yet effective generative
model based on atomic scene generation functions along with physical
constraints. Our experiments show that more than $60\%$ of the existing scenes
from the current benchmarks can be modified in a way to make prediction methods
fail (predicting off-road). We further show that (i) the generated scenes are
realistic since they do exist in the real world, and (ii) can be used to make
existing models robust by 30-40%. Code is available at
https://s-attack.github.io/.
Related papers
- Predicting Long-horizon Futures by Conditioning on Geometry and Time [49.86180975196375]
We explore the task of generating future sensor observations conditioned on the past.
We leverage the large-scale pretraining of image diffusion models which can handle multi-modality.
We create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes.
arXiv Detail & Related papers (2024-04-17T16:56:31Z) - Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic
Dataset and New Metrics [15.09892709945568]
We contribute the first video anomaly segmentation dataset for autonomous driving.
Our dataset consists of 120,000 high-resolution frames at a 60 FPS framerate, as recorded in 7 different towns.
We focus on two new metrics: temporal consistency and latencyaware streaming accuracy.
arXiv Detail & Related papers (2024-01-10T05:38:48Z) - Safe Real-World Autonomous Driving by Learning to Predict and Plan with
a Mixture of Experts [3.2230833657560503]
We propose a distribution over multiple future trajectories for both the self-driving vehicle and other road agents.
During inference, we select the planning trajectory that minimizes a cost taking into account safety and the predicted probabilities.
We successfully deploy it on a self-driving vehicle on urban public roads, confirming that it drives safely without compromising comfort.
arXiv Detail & Related papers (2022-11-03T20:16:24Z) - Model-Based Imitation Learning for Urban Driving [26.782783239210087]
We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for autonomous driving.
Our model is trained on an offline corpus of urban driving data, without any online interaction with the environment.
Our approach is the first camera-only method that models static scene, dynamic scene, and ego-behaviour in an urban driving environment.
arXiv Detail & Related papers (2022-10-14T11:59:46Z) - LOPR: Latent Occupancy PRediction using Generative Models [49.15687400958916]
LiDAR generated occupancy grid maps (L-OGMs) offer a robust bird's eye-view scene representation.
We propose a framework that decouples occupancy prediction into: representation learning and prediction within the learned latent space.
arXiv Detail & Related papers (2022-10-03T22:04:00Z) - Deep Generative Models for Vehicle Speed Trajectories [2.5137859989323537]
We show how extensions to deep generative models allow accurate and scalable generation.
Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.
arXiv Detail & Related papers (2021-12-14T20:14:03Z) - Are socially-aware trajectory prediction models really socially-aware? [75.36961426916639]
We introduce a socially-attended attack to assess the social understanding of prediction models.
An attack is a small yet carefully-crafted perturbations to fail predictors.
We show that our attack can be employed to increase the social understanding of state-of-the-art models.
arXiv Detail & Related papers (2021-08-24T17:59:09Z) - Injecting Knowledge in Data-driven Vehicle Trajectory Predictors [82.91398970736391]
Vehicle trajectory prediction tasks have been commonly tackled from two perspectives: knowledge-driven or data-driven.
In this paper, we propose to learn a "Realistic Residual Block" (RRB) which effectively connects these two perspectives.
Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty.
arXiv Detail & Related papers (2021-03-08T16:03:09Z) - SceneGen: Learning to Generate Realistic Traffic Scenes [92.98412203941912]
We present SceneGen, a neural autoregressive model of traffic scenes that eschews the need for rules and distributions.
We demonstrate SceneGen's ability to faithfully model distributions of real traffic scenes.
arXiv Detail & Related papers (2021-01-16T22:51:43Z) - Map-Adaptive Goal-Based Trajectory Prediction [3.1948816877289263]
We present a new method for multi-modal, long-term vehicle trajectory prediction.
Our approach relies on using lane centerlines captured in rich maps of the environment to generate a set of proposed goal paths for each vehicle.
We show that our model outperforms state-of-the-art approaches for vehicle trajectory prediction over a 6-second horizon.
arXiv Detail & Related papers (2020-09-09T17:57:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.