Interactive multi-modal motion planning with Branch Model Predictive Control. Chen, Y., Rosolia, U., Ubellacker, W., Csomay-Shanklin, N., & Ames, A. D. arXiv:2109.05128 [cs, eess], September, 2021. arXiv: 2109.05128![Interactive multi-modal motion planning with Branch Model Predictive Control [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Motion planning for autonomous robots and vehicles in presence of uncontrolled agents remains a challenging problem as the reactive behaviors of the uncontrolled agents must be considered. Since the uncontrolled agents usually demonstrate multimodal reactive behavior, the motion planner needs to solve a continuous motion planning problem under these behaviors, which contains a discrete element. We propose a branch Model Predictive Control (MPC) framework that plans over feedback policies to leverage the reactive behavior of the uncontrolled agent. In particular, a scenario tree is constructed from a finite set of policies of the uncontrolled agent, and the branch MPC solves for a feedback policy in the form of a trajectory tree, which shares the same topology as the scenario tree. Moreover, coherent risk measures such as the Conditional Value at Risk (CVaR) are used as a tuning knob to adjust the tradeoff between performance and robustness. The proposed branch MPC framework is tested on an overtake and lane change task and a merging task for autonomous vehicles in simulation, and on the motion planning of an autonomous quadruped robot alongside an uncontrolled quadruped in experiments. The result demonstrates interesting human-like behaviors, achieving a balance between safety and performance.
@article{chen_interactive_2021,
title = {Interactive multi-modal motion planning with {Branch} {Model} {Predictive} {Control}},
url = {http://arxiv.org/abs/2109.05128},
abstract = {Motion planning for autonomous robots and vehicles in presence of uncontrolled agents remains a challenging problem as the reactive behaviors of the uncontrolled agents must be considered. Since the uncontrolled agents usually demonstrate multimodal reactive behavior, the motion planner needs to solve a continuous motion planning problem under these behaviors, which contains a discrete element. We propose a branch Model Predictive Control (MPC) framework that plans over feedback policies to leverage the reactive behavior of the uncontrolled agent. In particular, a scenario tree is constructed from a finite set of policies of the uncontrolled agent, and the branch MPC solves for a feedback policy in the form of a trajectory tree, which shares the same topology as the scenario tree. Moreover, coherent risk measures such as the Conditional Value at Risk (CVaR) are used as a tuning knob to adjust the tradeoff between performance and robustness. The proposed branch MPC framework is tested on an overtake and lane change task and a merging task for autonomous vehicles in simulation, and on the motion planning of an autonomous quadruped robot alongside an uncontrolled quadruped in experiments. The result demonstrates interesting human-like behaviors, achieving a balance between safety and performance.},
language = {en},
urldate = {2022-03-16},
journal = {arXiv:2109.05128 [cs, eess]},
author = {Chen, Yuxiao and Rosolia, Ugo and Ubellacker, Wyatt and Csomay-Shanklin, Noel and Ames, Aaron D.},
month = sep,
year = {2021},
note = {arXiv: 2109.05128},
keywords = {Computer Science - Robotics, Electrical Engineering and Systems Science - Systems and Control},
}
Downloads: 0
{"_id":"AHopNgitBdqyFFJka","bibbaseid":"chen-rosolia-ubellacker-csomayshanklin-ames-interactivemultimodalmotionplanningwithbranchmodelpredictivecontrol-2021","author_short":["Chen, Y.","Rosolia, U.","Ubellacker, W.","Csomay-Shanklin, N.","Ames, A. D."],"bibdata":{"bibtype":"article","type":"article","title":"Interactive multi-modal motion planning with Branch Model Predictive Control","url":"http://arxiv.org/abs/2109.05128","abstract":"Motion planning for autonomous robots and vehicles in presence of uncontrolled agents remains a challenging problem as the reactive behaviors of the uncontrolled agents must be considered. Since the uncontrolled agents usually demonstrate multimodal reactive behavior, the motion planner needs to solve a continuous motion planning problem under these behaviors, which contains a discrete element. We propose a branch Model Predictive Control (MPC) framework that plans over feedback policies to leverage the reactive behavior of the uncontrolled agent. In particular, a scenario tree is constructed from a finite set of policies of the uncontrolled agent, and the branch MPC solves for a feedback policy in the form of a trajectory tree, which shares the same topology as the scenario tree. Moreover, coherent risk measures such as the Conditional Value at Risk (CVaR) are used as a tuning knob to adjust the tradeoff between performance and robustness. The proposed branch MPC framework is tested on an overtake and lane change task and a merging task for autonomous vehicles in simulation, and on the motion planning of an autonomous quadruped robot alongside an uncontrolled quadruped in experiments. The result demonstrates interesting human-like behaviors, achieving a balance between safety and performance.","language":"en","urldate":"2022-03-16","journal":"arXiv:2109.05128 [cs, eess]","author":[{"propositions":[],"lastnames":["Chen"],"firstnames":["Yuxiao"],"suffixes":[]},{"propositions":[],"lastnames":["Rosolia"],"firstnames":["Ugo"],"suffixes":[]},{"propositions":[],"lastnames":["Ubellacker"],"firstnames":["Wyatt"],"suffixes":[]},{"propositions":[],"lastnames":["Csomay-Shanklin"],"firstnames":["Noel"],"suffixes":[]},{"propositions":[],"lastnames":["Ames"],"firstnames":["Aaron","D."],"suffixes":[]}],"month":"September","year":"2021","note":"arXiv: 2109.05128","keywords":"Computer Science - Robotics, Electrical Engineering and Systems Science - Systems and Control","bibtex":"@article{chen_interactive_2021,\n\ttitle = {Interactive multi-modal motion planning with {Branch} {Model} {Predictive} {Control}},\n\turl = {http://arxiv.org/abs/2109.05128},\n\tabstract = {Motion planning for autonomous robots and vehicles in presence of uncontrolled agents remains a challenging problem as the reactive behaviors of the uncontrolled agents must be considered. Since the uncontrolled agents usually demonstrate multimodal reactive behavior, the motion planner needs to solve a continuous motion planning problem under these behaviors, which contains a discrete element. We propose a branch Model Predictive Control (MPC) framework that plans over feedback policies to leverage the reactive behavior of the uncontrolled agent. In particular, a scenario tree is constructed from a finite set of policies of the uncontrolled agent, and the branch MPC solves for a feedback policy in the form of a trajectory tree, which shares the same topology as the scenario tree. Moreover, coherent risk measures such as the Conditional Value at Risk (CVaR) are used as a tuning knob to adjust the tradeoff between performance and robustness. The proposed branch MPC framework is tested on an overtake and lane change task and a merging task for autonomous vehicles in simulation, and on the motion planning of an autonomous quadruped robot alongside an uncontrolled quadruped in experiments. The result demonstrates interesting human-like behaviors, achieving a balance between safety and performance.},\n\tlanguage = {en},\n\turldate = {2022-03-16},\n\tjournal = {arXiv:2109.05128 [cs, eess]},\n\tauthor = {Chen, Yuxiao and Rosolia, Ugo and Ubellacker, Wyatt and Csomay-Shanklin, Noel and Ames, Aaron D.},\n\tmonth = sep,\n\tyear = {2021},\n\tnote = {arXiv: 2109.05128},\n\tkeywords = {Computer Science - Robotics, Electrical Engineering and Systems Science - Systems and Control},\n}\n\n","author_short":["Chen, Y.","Rosolia, U.","Ubellacker, W.","Csomay-Shanklin, N.","Ames, A. D."],"key":"chen_interactive_2021","id":"chen_interactive_2021","bibbaseid":"chen-rosolia-ubellacker-csomayshanklin-ames-interactivemultimodalmotionplanningwithbranchmodelpredictivecontrol-2021","role":"author","urls":{"Paper":"http://arxiv.org/abs/2109.05128"},"keyword":["Computer Science - Robotics","Electrical Engineering and Systems Science - Systems and Control"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/users/5612529/collections/DGS34TEY/items?key=aiprMlXOSKe71AbbxNPHHfe7&format=bibtex&limit=100","dataSources":["qAk5kJqscSPPSguqo","itnDcZtAo5EAWcXeE","JyoDgr7qvkjGYcFft","aeHt7AWKsAw9iiQqD"],"keywords":["computer science - robotics","electrical engineering and systems science - systems and control"],"search_terms":["interactive","multi","modal","motion","planning","branch","model","predictive","control","chen","rosolia","ubellacker","csomay-shanklin","ames"],"title":"Interactive multi-modal motion planning with Branch Model Predictive Control","year":2021}