Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networks

• URL: http://arxiv.org/abs/2103.01644v1
• Date: Tue, 2 Mar 2021 11:13:43 GMT
• Title: Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networks
• Authors: Albert Dulian and John C. Murray
• Abstract summary: This paper explores use of Capsule Networks (CapsNets) in the context of learning a hierarchical representation of sparse semantic layers corresponding to small regions of the High-Definition (HD) map. By using an architecture based on CapsNets the model is able to retain hierarchical relationships between detected features within images whilst also preventing loss of spatial data often caused by the pooling operation. We show that our model achieves significant improvement over recently published works on prediction, whilst drastically reducing the overall size of the network.
• Score: 0.12183405753834559
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As urban environments manifest high levels of complexity it is of vital importance that safety systems embedded within autonomous vehicles (AVs) are able to accurately anticipate short-term future motion of nearby agents. This problem can be further understood as generating a sequence of coordinates describing the future motion of the tracked agent. Various proposed approaches demonstrate significant benefits of using a rasterised top-down image of the road, with a combination of Convolutional Neural Networks (CNNs), for extraction of relevant features that define the road structure (eg. driveable areas, lanes, walkways). In contrast, this paper explores use of Capsule Networks (CapsNets) in the context of learning a hierarchical representation of sparse semantic layers corresponding to small regions of the High-Definition (HD) map. Each region of the map is dismantled into separate geometrical layers that are extracted with respect to the agent's current position. By using an architecture based on CapsNets the model is able to retain hierarchical relationships between detected features within images whilst also preventing loss of spatial data often caused by the pooling operation. We train and evaluate our model on publicly available dataset nuTonomy scenes and compare it to recently published methods. We show that our model achieves significant improvement over recently published works on deterministic prediction, whilst drastically reducing the overall size of the network.

Related papers

• Radio Map Prediction from Aerial Images and Application to Coverage Optimization [46.870065000932016]
  We focus on predicting path loss radio maps using convolutional neural networks. We show that state-of-the-art models developed for existing radio map datasets can be effectively adapted to this task. We introduce a new model that slightly exceeds the performance of the present state-of-the-art with reduced complexity.
  arXiv  Detail & Related papers  (2024-10-07T09:19:20Z)
• Traffic Prediction considering Multiple Levels of Spatial-temporal Information: A Multi-scale Graph Wavelet-based Approach [3.343804744266258]
  This study proposes a graph wavelet temporal convolution network (MSGWTCN) to predict the traffic states in complex transportation networks. Two real-world datasets are used to investigate the model performance, including a highway network in Seattle and a dense road network of Manhattan in New York City.
  arXiv  Detail & Related papers  (2024-06-18T20:05:47Z)
• Exploring Geometric Deep Learning For Precipitation Nowcasting [28.44612565923532]
  We propose a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting. The adjacency matrix that simulates the interactions among grid cells is learned automatically by minimizing the L1 loss between prediction and ground truth pixel value. We test the model on sequences of radar reflectivity maps over the Trento/Italy area.
  arXiv  Detail & Related papers  (2023-09-11T21:14:55Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• Network Embedding via Deep Prediction Model [25.727377978617465]
  This paper proposes a network embedding framework to capture the transfer behaviors on structured networks via deep prediction models. A network structure embedding layer is added into conventional deep prediction models, including Long Short-Term Memory Network and Recurrent Neural Network. Experimental studies are conducted on various datasets including social networks, citation networks, biomedical network, collaboration network and language network.
  arXiv  Detail & Related papers  (2021-04-27T16:56:00Z)
• SST-GNN: Simplified Spatio-temporal Traffic forecasting model using Graph Neural Network [2.524966118517392]
  We have designed a simplified S-temporal GNN(SST-GNN) that effectively encodes the dependency by separately aggregating different neighborhood. We have shown that our model has significantly outperformed the state-of-the-art models on three real-world traffic datasets.
  arXiv  Detail & Related papers  (2021-03-31T18:28:44Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Learning Lane Graph Representations for Motion Forecasting [92.88572392790623]
  We construct a lane graph from raw map data to preserve the map structure. We exploit a fusion network consisting of four types of interactions, actor-to-lane, lane-to-lane, lane-to-actor and actor-to-actor. Our approach significantly outperforms the state-of-the-art on the large scale Argoverse motion forecasting benchmark.
  arXiv  Detail & Related papers  (2020-07-27T17:59:49Z)
• VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation [74.56282712099274]
  This paper introduces VectorNet, a hierarchical graph neural network that exploits the spatial locality of individual road components represented by vectors. By operating on the vectorized high definition (HD) maps and agent trajectories, we avoid lossy rendering and computationally intensive ConvNet encoding steps. We evaluate VectorNet on our in-house behavior prediction benchmark and the recently released Argoverse forecasting dataset.
  arXiv  Detail & Related papers  (2020-05-08T19:07:03Z)
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting [88.5550074808201]
  We propose Geographic and Long term Temporal Graph Convolutional Recurrent Neural Network (GLT-GCRNN) for traffic forecasting. In this work, we propose a novel framework for traffic forecasting that learns the rich interactions between roads sharing similar geographic or longterm temporal patterns.
  arXiv  Detail & Related papers  (2020-04-23T03:50:46Z)
• A Spatial-Temporal Attentive Network with Spatial Continuity for Trajectory Prediction [74.00750936752418]
  We propose a novel model named spatial-temporal attentive network with spatial continuity (STAN-SC) First, spatial-temporal attention mechanism is presented to explore the most useful and important information. Second, we conduct a joint feature sequence based on the sequence and instant state information to make the generative trajectories keep spatial continuity.
  arXiv  Detail & Related papers  (2020-03-13T04:35:50Z)

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.