1 code implementation • 12 Apr 2024 • Dvij Kalaria, Shreya Sharma, Sarthak Bhagat, Haoru Xue, John M. Dolan
Off-road navigation is a challenging problem both at the planning level to get a smooth trajectory and at the control level to avoid flipping over, hitting obstacles, or getting stuck at a rough patch.
no code implementations • 1 Nov 2023 • Simin Liu, Kai S. Yun, John M. Dolan, Changliu Liu
Our raCBFs are currently the most effective way to guarantee safety for uncertain systems, achieving 100% safety and up to 55% performance improvement over a robust baseline.
no code implementations • 25 Aug 2023 • Dvij Kalaria, Qin Lin, John M. Dolan
In this work, we propose a curriculum learning-based framework by transitioning from a simpler vehicle model to a more complex real environment to teach the reinforcement learning agent a policy closer to the optimal policy.
no code implementations • 22 May 2023 • Yiwei Lyu, Wenhao Luo, John M. Dolan
Decentralized control schemes are increasingly favored in various domains that involve multi-agent systems due to the need for computational efficiency as well as general applicability to large-scale systems.
no code implementations • 10 Jul 2022 • Shivesh Khaitan, John M. Dolan
In this work, we address the problem of traversing unsignalized intersections using a novel curriculum for deep reinforcement learning.
no code implementations • 26 Apr 2022 • Ian Char, Viraj Mehta, Adam Villaflor, John M. Dolan, Jeff Schneider
Past efforts for developing algorithms in this area have revolved around introducing constraints to online reinforcement learning algorithms to ensure the actions of the learned policy are constrained to the logged data.
no code implementations • 22 Mar 2021 • Christoph Killing, Adam Villaflor, John M. Dolan
We train policies to robustly negotiate with opposing vehicles of an unobservable degree of cooperativeness using multi-agent reinforcement learning (MARL).
1 code implementation • 9 Nov 2020 • Kaleb Ben Naveed, Zhiqian Qiao, John M. Dolan
The problem of incomplete observations is handled by using a Long-Short-Term-Memory (LSTM) layer in the network.
no code implementations • 9 Nov 2020 • Josiah Coad, Zhiqian Qiao, John M. Dolan
Self-driving vehicles must be able to act intelligently in diverse and difficult environments, marked by high-dimensional state spaces, a myriad of optimization objectives and complex behaviors.
no code implementations • 9 Nov 2020 • Zhiqian Qiao, Jeff Schneider, John M. Dolan
In this work, we propose a behavior planning structure based on reinforcement learning (RL) which is capable of performing autonomous vehicle behavior planning with a hierarchical structure in simulated urban environments.
no code implementations • 3 Sep 2020 • Chen Fu, Chiyu Dong, Christoph Mertz, John M. Dolan
This late-fusion block uses the dense context features to guide the depth prediction based on demonstrations by sparse depth features.
no code implementations • 9 Nov 2019 • Zhiqian Qiao, Zachariah Tyree, Priyantha Mudalige, Jeff Schneider, John M. Dolan
In this work, we propose a hierarchical reinforcement learning (HRL) structure which is capable of performing autonomous vehicle planning tasks in simulated environments with multiple sub-goals.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 9 Nov 2019 • Zhiqian Qiao, Jing Zhao, Zachariah Tyree, Priyantha Mudalige, Jeff Schneider, John M. Dolan
How autonomous vehicles and human drivers share public transportation systems is an important problem, as fully automatic transportation environments are still a long way off.
no code implementations • 3 Oct 2019 • Chen Fu, Chiyu Dong, Xiao Zhang, John M. Dolan
Based on our previous optimization/criteria-based L-Shape fitting algorithm, we here propose a data-driven and model-based method for robust vehicle segmentation and tracking.
no code implementations • 19 Dec 2018 • Yilun Chen, Praveen Palanisamy, Priyantha Mudalige, Katharina Muelling, John M. Dolan
In this paper, we leverage auxiliary information aside from raw images and design a novel network structure, called Auxiliary Task Network (ATN), to help boost the driving performance while maintaining the advantage of minimal training data and an End-to-End training method.
no code implementations • 27 May 2013 • Kian Hsiang Low, John M. Dolan, Pradeep Khosla
The time complexity of solving MASP approximately depends on the map resolution, which limits its use in large-scale, high-resolution exploration and mapping.