Meta-Learning over Time for Destination Prediction Tasks
- URL: http://arxiv.org/abs/2206.14801v1
- Date: Wed, 29 Jun 2022 17:58:12 GMT
- Title: Meta-Learning over Time for Destination Prediction Tasks
- Authors: Mark Tenzer, Zeeshan Rasheed, Khurram Shafique, Nuno Vasconcelos
- Abstract summary: A need to understand and predict vehicles' behavior underlies both public and private goals in the transportation domain.
Recent studies have found, at best, only marginal improvements in predictive performance from incorporating temporal information.
We propose an approach based on hypernetworks, in which a neural network learns to change its own weights in response to an input.
- Score: 53.12827614887103
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A need to understand and predict vehicles' behavior underlies both public and
private goals in the transportation domain, including urban planning and
management, ride-sharing services, and intelligent transportation systems.
Individuals' preferences and intended destinations vary throughout the day,
week, and year: for example, bars are most popular in the evenings, and beaches
are most popular in the summer. Despite this principle, we note that recent
studies on a popular benchmark dataset from Porto, Portugal have found, at
best, only marginal improvements in predictive performance from incorporating
temporal information. We propose an approach based on hypernetworks, a variant
of meta-learning ("learning to learn") in which a neural network learns to
change its own weights in response to an input. In our case, the weights
responsible for destination prediction vary with the metadata, in particular
the time, of the input trajectory. The time-conditioned weights notably improve
the model's error relative to ablation studies and comparable prior work, and
we confirm our hypothesis that knowledge of time should improve prediction of a
vehicle's intended destination.
Related papers
- MetaFollower: Adaptable Personalized Autonomous Car Following [63.90050686330677]
We propose an adaptable personalized car-following framework - MetaFollower.
We first utilize Model-Agnostic Meta-Learning (MAML) to extract common driving knowledge from various CF events.
We additionally combine Long Short-Term Memory (LSTM) and Intelligent Driver Model (IDM) to reflect temporal heterogeneity with high interpretability.
arXiv Detail & Related papers (2024-06-23T15:30:40Z) - Valeo4Cast: A Modular Approach to End-to-End Forecasting [93.86257326005726]
Our solution ranks first in the Argoverse 2 End-to-end Forecasting Challenge, with 63.82 mAPf.
We depart from the current trend of tackling this task via end-to-end training from perception to forecasting, and instead use a modular approach.
We surpass forecasting results by +17.1 points over last year's winner and by +13.3 points over this year's runner-up.
arXiv Detail & Related papers (2024-06-12T11:50:51Z) - STDA-Meta: A Meta-Learning Framework for Few-Shot Traffic Prediction [5.502177196766933]
We propose a novel-temporal domain adaptation (STDA) method that learns transferable meta-knowledge from data-sufficient cities in an adversarial manner.
This learned meta-knowledge can improve prediction performance of data-scarce cities.
Specifically, we train the STDA model using a Model-Atemporal Meta-Learning (MAML) based episode learning process.
arXiv Detail & Related papers (2023-10-31T06:52:56Z) - Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems
Using Optimal Transport [89.61692654941106]
We propose a new approach to predicting such mass flow over time using optimal transport.
We apply our approach to the task of predicting how communities will evolve over time in social network settings.
arXiv Detail & Related papers (2023-03-14T07:25:44Z) - How do you go where? Improving next location prediction by learning
travel mode information using transformers [6.003006906852134]
We propose a transformer decoder-based neural network to predict the next location an individual will visit based on historical locations, time, and travel modes.
In particular, the prediction of the next travel mode is designed as an auxiliary task to help guide the network's learning.
Our experiments show that the proposed method significantly outperforms other state-of-the-art next location prediction methods.
arXiv Detail & Related papers (2022-10-08T19:36:58Z) - Control-Aware Prediction Objectives for Autonomous Driving [78.19515972466063]
We present control-aware prediction objectives (CAPOs) to evaluate the downstream effect of predictions on control without requiring the planner be differentiable.
We propose two types of importance weights that weight the predictive likelihood: one using an attention model between agents, and another based on control variation when exchanging predicted trajectories for ground truth trajectories.
arXiv Detail & Related papers (2022-04-28T07:37:21Z) - Boosting Algorithms for Delivery Time Prediction in Transportation
Logistics [2.147325264113341]
We show that travel time prediction can help mitigate high delays in postal services.
Some boosting algorithms, such as light gradient boosting and catboost, have a higher performance in terms of accuracy and runtime efficiency.
arXiv Detail & Related papers (2020-09-24T11:01:22Z) - BusTime: Which is the Right Prediction Model for My Bus Arrival Time? [3.1761486589684975]
This paper tries to fill this gap by proposing a general and practical evaluation framework for analysing various widely used prediction models.
In particular, this framework contains a raw bus GPS data pre-processing method that needs much less number of input data points.
We also present preliminary results for city managers by analysing the practical strengths and weaknesses in both training and predicting stages of commonly used prediction models.
arXiv Detail & Related papers (2020-03-20T17:03:36Z) - Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction [57.56466850377598]
Reasoning over visual data is a desirable capability for robotics and vision-based applications.
In this paper, we present a framework on graph to uncover relationships in different objects in the scene for reasoning about pedestrian intent.
Pedestrian intent, defined as the future action of crossing or not-crossing the street, is a very crucial piece of information for autonomous vehicles.
arXiv Detail & Related papers (2020-02-20T18:50:44Z)
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.