Allo-centric Occupancy Grid Prediction for Urban Traffic Scene Using Video Prediction Networks

Asghar, Rabbia; Rummelhard, Lukas; Spalanzani, Anne; Laugier, Christian

doi:10.1109/icarcv57592.2022.10004321

Cited by 3 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, research has been conducted on integrating maps with semantic information using LiDAR, specifically employing the PointPillar approach for semantic labeling. This study combines spatiotemporal and conditional variational deep learning methods to detect vehicles [12]. Another study combines DOGMs and object-level tracking using LiDAR.…”

Section: Dynamic Occupancy Grid Maps (Dogms)mentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion

Jang,

Kim,

Ahn

et al. 2024

Sensors

View full text Add to dashboard Cite

In the field of robotics and autonomous driving, dynamic occupancy grid maps (DOGMs) are typically used to represent the position and velocity information of objects. Although three-dimensional light detection and ranging (LiDAR) sensor-based DOGMs have been actively researched, they have limitations, as they cannot classify types of objects. Therefore, in this study, a deep learning-based camera–LiDAR sensor fusion technique is employed as input to DOGMs. Consequently, not only the position and velocity information of objects but also their class information can be updated, expanding the application areas of DOGMs. Moreover, unclassified LiDAR point measurements contribute to the formation of a map of the surrounding environment, improving the reliability of perception by registering objects that were not classified by deep learning. To achieve this, we developed update rules on the basis of the Dempster–Shafer evidence theory, incorporating class information and the uncertainty of objects occupying grid cells. Furthermore, we analyzed the accuracy of the velocity estimation using two update models. One assigns the occupancy probability only to the edges of the oriented bounding box, whereas the other assigns the occupancy probability to the entire area of the box. The performance of the developed perception technique is evaluated using the public nuScenes dataset. The developed DOGM with object class information will help autonomous vehicles to navigate in complex urban driving environments by providing them with rich information, such as the class and velocity of nearby obstacles.

show abstract

Section: Dynamic Occupancy Grid Maps (Dogms)mentioning

confidence: 99%

“…Similarly, the weights associated with the occupancy mass (m c b,t+1 ) and the label mass (m c b,l,t+1 ) for the newborn grids are calculated using (12).…”

Section: Sensor Fusion Dogmmentioning

confidence: 99%

Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion

Jang,

Kim,

Ahn

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Previous works by Mann et al [21] and Asghar et al [22] present occupancy grid prediction models that use semantic labels of the occupied cells to improve prediction. Semantic labels consist of only vehicle information in both of these approaches, whereas our proposed SMGMs contain other semantic labels in addition to the vehicle labels (e.g., vehicles, cyclists, pedestrians).…”

Section: A Predicting Future Occupancy Statesmentioning

confidence: 99%

Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban Environments

Toyungyernsub

Yel

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

For autonomous vehicles to proactively plan safe trajectories and make informed decisions, they must be able to predict the future occupancy states of the local environment. However, common issues with occupancy prediction include predictions where moving objects vanish or become blurred, particularly at longer time horizons. We propose an environment prediction framework that incorporates environment semantics for future occupancy prediction. Our method first semantically segments the environment and uses this information along with the occupancy information to predict the spatiotemporal evolution of the environment. We validate our approach on the real-world Waymo Open Dataset. Compared to baseline methods, our model has higher prediction accuracy and is capable of maintaining moving object appearances in the predictions for longer prediction time horizons.

show abstract

Vehicle Motion Forecasting Using Prior Information and Semantic-Assisted Occupancy Grid Maps

Asghar,

Diaz-Zapata,

Rummelhard

et al. 2023

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Allo-centric Occupancy Grid Prediction for Urban Traffic Scene Using Video Prediction Networks

Cited by 3 publications

References 36 publications

Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion

Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion

Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban Environments

Vehicle Motion Forecasting Using Prior Information and Semantic-Assisted Occupancy Grid Maps

Contact Info

Product

Resources

About