no code implementations • 26 Mar 2024 • Kashyap Chitta, Daniel Dauner, Andreas Geiger
SLEDGE is the first generative simulator for vehicle motion planning trained on real-world driving logs.
1 code implementation • 14 Mar 2024 • Jiazhi Yang, Shenyuan Gao, Yihang Qiu, Li Chen, Tianyu Li, Bo Dai, Kashyap Chitta, Penghao Wu, Jia Zeng, Ping Luo, Jun Zhang, Andreas Geiger, Yu Qiao, Hongyang Li
In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline.
1 code implementation • 21 Dec 2023 • Chonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Ping Luo, Andreas Geiger, Hongyang Li
The experiments demonstrate that Graph VQA provides a simple, principled framework for reasoning about a driving scene, and DriveLM-Data provides a challenging benchmark for this task.
no code implementations • 24 Aug 2023 • Tim Schreier, Katrin Renz, Andreas Geiger, Kashyap Chitta
Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly.
1 code implementation • 29 Jun 2023 • Li Chen, Penghao Wu, Kashyap Chitta, Bernhard Jaeger, Andreas Geiger, Hongyang Li
The autonomous driving community has witnessed a rapid growth in approaches that embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle motion plans, instead of concentrating on individual tasks such as detection and motion prediction.
1 code implementation • ICCV 2023 • Bernhard Jaeger, Kashyap Chitta, Andreas Geiger
End-to-end driving systems have recently made rapid progress, in particular on CARLA.
Ranked #1 on CARLA MAP Leaderboard on CARLA
2 code implementations • 13 Jun 2023 • Daniel Dauner, Marcel Hallgarten, Andreas Geiger, Kashyap Chitta
The release of nuPlan marks a new era in vehicle motion planning research, offering the first large-scale real-world dataset and evaluation schemes requiring both precise short-term planning and long-horizon ego-forecasting.
1 code implementation • 25 Oct 2022 • Katrin Renz, Kashyap Chitta, Otniel-Bogdan Mercea, A. Sophia Koepke, Zeynep Akata, Andreas Geiger
Planning an optimal route in a complex environment requires efficient reasoning about the surrounding scene.
Ranked #6 on CARLA longest6 on CARLA
3 code implementations • 31 May 2022 • Kashyap Chitta, Aditya Prakash, Bernhard Jaeger, Zehao Yu, Katrin Renz, Andreas Geiger
At the time of submission, TransFuser outperforms all prior work on the CARLA leaderboard in terms of driving score by a large margin.
Ranked #6 on Autonomous Driving on CARLA Leaderboard
1 code implementation • 28 Apr 2022 • Niklas Hanselmann, Katrin Renz, Kashyap Chitta, Apratim Bhattacharyya, Andreas Geiger
Simulators offer the possibility of safe, low-cost development of self-driving systems.
3 code implementations • NeurIPS 2021 • Axel Sauer, Kashyap Chitta, Jens Müller, Andreas Geiger
Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train.
Ranked #1 on Image Generation on Stanford Cars
1 code implementation • ICCV 2021 • Kashyap Chitta, Aditya Prakash, Andreas Geiger
Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving.
Ranked #4 on Novel View Synthesis on X3D
2 code implementations • CVPR 2021 • Aditya Prakash, Kashyap Chitta, Andreas Geiger
How should representations from complementary sensors be integrated for autonomous driving?
Ranked #1 on Autonomous Driving on Town05 Short
1 code implementation • 12 Jun 2020 • Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding.
3 code implementations • 20 May 2020 • Aseem Behl, Kashyap Chitta, Aditya Prakash, Eshed Ohn-Bar, Andreas Geiger
Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
no code implementations • 9 Apr 2020 • Elmar Haussmann, Michele Fenzi, Kashyap Chitta, Jan Ivanecky, Hanson Xu, Donna Roy, Akshita Mittel, Nicolas Koumchatzky, Clement Farabet, Jose M. Alvarez
We have built a scalable production system for active learning in the domain of autonomous driving.
no code implementations • 25 Sep 2019 • Kashyap Chitta, Jose M. Alvarez, Elmar Haussmann, Clement Farabet
In this paper, we propose to scale up ensemble Active Learning methods to perform acquisition at a large scale (10k to 500k samples at a time).
1 code implementation • 27 Jul 2019 • Kashyap Chitta, Jose M. Alvarez, Martial Hebert
Semantic segmentation with Convolutional Neural Networks is a memory-intensive task due to the high spatial resolution of feature maps and output predictions.
no code implementations • 29 May 2019 • Kashyap Chitta, Jose M. Alvarez, Elmar Haussmann, Clement Farabet
In this paper, we propose to scale up ensemble Active Learning (AL) methods to perform acquisition at a large scale (10k to 500k samples at a time).
no code implementations • 8 Nov 2018 • Kashyap Chitta, Jianwei Feng, Martial Hebert
With our design, the network progressively learns features specific to the target domain using annotation from only the source domain.
no code implementations • 8 Nov 2018 • Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski
Annotating the right data for training deep neural networks is an important challenge.
no code implementations • 6 Nov 2018 • Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski
In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep Bayesian Neural Network (BNN).
no code implementations • 1 Jun 2018 • Kashyap Chitta
We propose Attentive Regularization (AR), a method to constrain the activation maps of kernels in Convolutional Neural Networks (CNNs) to specific regions of interest (ROIs).
no code implementations • 19 May 2018 • Yash Patel, Kashyap Chitta, Bhavan Jasani
We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning.