Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks

Schreiber, Marcel; Belagiannis, Vasileios; Gläser, Claudius; Dietmayer, Klaus

doi:10.1109/icra40945.2020.9196702

Cited by 20 publications

(28 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LSTM network is trained in simulation with traces of a coordinated strategy in 2D simple environment, then the trained network is embedded on each agent. Another work in [16] predicts dynamic environment presented as 2D occupancy grid map. This proposed work used ConvLSTM to capture the spatio-temporal features in grid maps in order to predict the next occupancy map status and the velocity.…”

Section: Related Workmentioning

confidence: 99%

“…Other work in the literature uses an approach for path prediction using Long Short Term Memory (LSTM). It has been used for various applications such as prediction of pedestrians' trajectory [14], motion planning [15], and occupancy 2D map prediction [16]. Most of the work utilizing LSTM predict trajectories in 2D space because of the increased complexity when extra dimensional data is considered [4], [16].…”

Section: Introductionmentioning

confidence: 99%

“…It has been used for various applications such as prediction of pedestrians' trajectory [14], motion planning [15], and occupancy 2D map prediction [16]. Most of the work utilizing LSTM predict trajectories in 2D space because of the increased complexity when extra dimensional data is considered [4], [16]. The ML in different fields is shifting toward the new paradigm of hybrid approaches which balances between conventional and ML approaches [17], [18].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Robot Hybrid Coverage Path Planning for 3D Reconstruction of Large Structures

Almadhoun

Taha²,

Seneviratne

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Coverage Path Planning (CPP) is an essential capability for autonomous robots operating in various critical applications such as fire fighting, and inspection. Performing autonomous coverage using a single robot system consumes time and energy. In particular, 3D large structures might contain some complex and occluded areas that shall be scanned rapidly in certain application domains. In this paper, a new Hybrid Coverage Path Planning (HCPP) approach is proposed to explore and cover unknown 3D large structures using a decentralized multi-robot system. The HCPP approach combines a guided Next Best View (NBV) approach with a developed Long Short Term Memory (LSTM) waypoint prediction approach to decrease the CPP exploration time at each iteration and simultaneously achieve high coverage. The hybrid approach is the new ML paradigm which fosters intelligence by balancing between data efficiency and generality allowing the exchange of some CPP parts with a learned model. The HCPP uses a stateful LSTM network architecture which is trained based on collected paths that cover different 3D structures to predict the next viewpoint. This architecture captures the dynamic dependencies of adjacent viewpoints in the long term sequences like the coverage paths. The HCPP switches between these methods triggered by either the number of iterations or an entropy threshold. In the decentralized multi-robot system, the proposed HCPP is embedded in each robot where each one of them shares its global 3D map ensuring robustness. The results performed in a realistic Gazebo robotic simulator confirmed the advantage of the proposed HCPP approach by achieving high coverage on different 3D unknown structures in a shorter time compared to conventional NBV.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Robot Hybrid Coverage Path Planning for 3D Reconstruction of Large Structures

Almadhoun

Taha²,

Seneviratne

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Therefore, grid maps are utilized in variety of machine learning applications, e.g. object detection [9] and motion estimation [10]. Despite being computationally efficient, grip mapping suffers from an information bottleneck due to the hand-crafted feature extraction, generally leading to a suboptimal performance.…”

Section: A Point Cloud Representationmentioning

confidence: 99%

PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data

Fei

Peng

Heidenreich³

et al. 2021

2021 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

“…However, the aforementioned particle-based approaches for estimating DOGMs come with mainly two drawbacks: the assumption of independent cells in the update step of the particle filter and the high computational effort due to the particle approximation. To tackle these drawbacks, we have proposed in prior work [8] a learning-based approach for predicting DOGMs in a setting with stationary egovehicle. Here, we have shown, that a learning-based approach provides more accurate velocity estimates in dynamic driving situations, e.g.…”

Section: Introductionmentioning

confidence: 99%