Sorin Mihai Grigorescu — accepted AI-conference papers

2021

ObserveNet Control: A Vision-Dynamics Learning Approach to Predictive Control in Autonomous Vehicles

Cosmin Ginerica, Mihai V. Zaha, Florin Gogianu, Lucian Busoniu, Bogdan Trasnea, Sorin Mihai Grigorescu

RA-L 2021

A key component in autonomous driving is the ability of the self-driving car to understand, track and predict the dynamics of the surrounding environment. Although there is significant work in the area of object detection, tracking and observations prediction, there is no prior work demonstrating th

Cited by 9 Source ↗Scholar ↗

2020

GFPNet: A Deep Network for Learning Shape Completion in Generic Fitted Primitives

Tiberiu T. Cocias, Alexandru Razvant, Sorin Mihai Grigorescu

RA-L 2020

In this letter, we propose an object reconstruction apparatus that uses the so-called Generic Primitives (GP) to complete shapes. A GP is a 3D point cloud depicting a generalized shape of a class of objects. To reconstruct the objects in a scene we first fit a GP onto each occluded object to obtain

Cited by 5 Source ↗Scholar ↗

2019

NeuroTrajectory: A Neuroevolutionary Approach to Local State Trajectory Learning for Autonomous Vehicles

Sorin Mihai Grigorescu, Bogdan Trasnea, Liviu Marina, Andrei Vasilcoi, Tiberiu T. Cocias

RA-L 2019

Autonomous vehicles are controlled today either based on sequences of decoupled perception-planning-action operations, either based on End2End or deep reinforcement learning (DRL) systems. Current deep learning solutions for autonomous driving are subject to several limitations (e.g., they estimate

Cited by 40 Source ↗Scholar ↗