Allen Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Allen Wang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Charles Dawson
Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, USA
5 shared publicationsChuchu Fan
Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, USA
5 shared publicationsCristina Rea
Plasma Science and Fusion Center, Massachusetts Institute of Technology, Cambridge, USA
5 shared publicationsOswin So
Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, USA
5 shared publications- Ashkan Jasour
University of Michigan 48109 Ann Arbor MI USA
3 shared publications - Brian Charles Williams
Massachusetts Institute of Technology
3 shared publications
Latest Publications
- Open Access
- 6 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-16
Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV
The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM’s ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.
- 6 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-16
Open AccessLearning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV
The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM’s ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.
- Open Access
- 4 June 2025
- Published by Springer Nature in Communications Physics
- Vol. 8 (1) , 1-13
Active ramp-down control and trajectory design for tokamaks with neural differential equations and reinforcement learning
- 4 June 2025
- Published by Springer Nature in Communications Physics
- Vol. 8 (1) , 1-13
Open AccessActive ramp-down control and trajectory design for tokamaks with neural differential equations and reinforcement learning
- Open Access
- 13 March 2025
- Published by Springer Nature in Research Square
Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV
The rampdown in tokamak operations is a difficult to simulate phase during which the plasma is often pushed towards multiple instability limits. To address this challenge, and reduce the risk of disrupting operations, we leverage recent advances in Scientific Machine Learning (SciML) to develop a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. By integrating simple physics structure and data-driven models, the NSSM efficiently learns plasma dynamics during the rampdown from a modest dataset of 311 pulses with only five pulses in the reactor relevant high performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid multiple instability limits with high probability. Experiments at TCV ramping down high performance plasmas show statistically significant improvements in current and energy at plasma termination, with improvements in speed through continuous re-training. A predict-first experiment, increasing plasma current by 20\% from baseline, demonstrates the NSSM's ability to make small extrapolations with sufficient accuracy to design trajectories that successfully terminate the pulse. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty, and demonstrates the relevance of the SciML approach to learning plasma dynamics for rapidly developing robust trajectories and controls during the incremental campaigns of upcoming burning plasma tokamaks.
- 13 March 2025
- Published by Springer Nature in Research Square
Open AccessLearning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV
The rampdown in tokamak operations is a difficult to simulate phase during which the plasma is often pushed towards multiple instability limits. To address this challenge, and reduce the risk of disrupting operations, we leverage recent advances in Scientific Machine Learning (SciML) to develop a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. By integrating simple physics structure and data-driven models, the NSSM efficiently learns plasma dynamics during the rampdown from a modest dataset of 311 pulses with only five pulses in the reactor relevant high performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid multiple instability limits with high probability. Experiments at TCV ramping down high performance plasmas show statistically significant improvements in current and energy at plasma termination, with improvements in speed through continuous re-training. A predict-first experiment, increasing plasma current by 20\% from baseline, demonstrates the NSSM's ability to make small extrapolations with sufficient accuracy to design trajectories that successfully terminate the pulse. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty, and demonstrates the relevance of the SciML approach to learning plasma dynamics for rapidly developing robust trajectories and controls during the incremental campaigns of upcoming burning plasma tokamaks.
- Open Access
- 7 November 2024
- Published by Springer Nature in Research Square
Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning
The tokamak offers a promising path to fusion energy, but disruptions pose a major economic risk, motivating advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation is massively parallelized on GPU with randomized parameters during policy training. The trained policy is then transferred to a transport simulator where it successfully ramps down the plasma. We directly address the crucial issue of safety criticality by demonstrating that a constraint-conditioned policy can be a trajectory design assistant that designs a library of feed-forward trajectories to handle conditions and user settings, a promising approach for the safety-critical context of burning plasma tokamaks. Finally, we demonstrate that the training environment can be a useful platform for other feed-forward optimization approaches by using an evolutionary algorithm to optimize feed-forward trajectories that are robust to physics uncertainty.
- 7 November 2024
- Published by Springer Nature in Research Square
Open AccessActive Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning
The tokamak offers a promising path to fusion energy, but disruptions pose a major economic risk, motivating advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation is massively parallelized on GPU with randomized parameters during policy training. The trained policy is then transferred to a transport simulator where it successfully ramps down the plasma. We directly address the crucial issue of safety criticality by demonstrating that a constraint-conditioned policy can be a trajectory design assistant that designs a library of feed-forward trajectories to handle conditions and user settings, a promising approach for the safety-critical context of burning plasma tokamaks. Finally, we demonstrate that the training environment can be a useful platform for other feed-forward optimization approaches by using an evolutionary algorithm to optimize feed-forward trajectories that are robust to physics uncertainty.
- Open Access
Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning
The tokamak offers a promising path to fusion energy, but plasma disruptions pose a major economic risk, motivating considerable advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation environment is massively parallelized on GPU with randomized physics parameters during policy training. The trained policy is then successfully transferred to a higher fidelity simulator where it successfully ramps down the plasma while avoiding user-specified disruptive limits. We also address the crucial issue of safety criticality by demonstrating that a constraint-conditioned policy can be used as a trajectory design assistant to design a library of feed-forward trajectories to handle different physics conditions and user settings. As a library of trajectories is more interpretable and verifiable offline, we argue such an approach is a promising path for leveraging the capabilities of reinforcement learning in the safety-critical context of burning plasma tokamaks. Finally, we demonstrate how the training environment can be a useful platform for other feed-forward optimization approaches by using an evolutionary algorithm to perform optimization of feed-forward trajectories that are robust to physics uncertainty
Open AccessActive Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning
The tokamak offers a promising path to fusion energy, but plasma disruptions pose a major economic risk, motivating considerable advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation environment is massively parallelized on GPU with randomized physics parameters during policy training. The trained policy is then successfully transferred to a higher fidelity simulator where it successfully ramps down the plasma while avoiding user-specified disruptive limits. We also address the crucial issue of safety criticality by demonstrating that a constraint-conditioned policy can be used as a trajectory design assistant to design a library of feed-forward trajectories to handle different physics conditions and user settings. As a library of trajectories is more interpretable and verifiable offline, we argue such an approach is a promising path for leveraging the capabilities of reinforcement learning in the safety-critical context of burning plasma tokamaks. Finally, we demonstrate how the training environment can be a useful platform for other feed-forward optimization approaches by using an evolutionary algorithm to perform optimization of feed-forward trajectories that are robust to physics uncertainty
- 25 November 2021
- Published by Springer Nature in Autonomous Robots
- Vol. 46 (1) , 269-282
Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures
- 25 November 2021
- Published by Springer Nature in Autonomous Robots
- Vol. 46 (1) , 269-282
Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures
- 21 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (4) , 6041-6048
Non-Gaussian Chance-Constrained Trajectory Planning for Autonomous Vehicles Under Agent Uncertainty
Agent behavior is arguably the greatest source of uncertainty in trajectory planning for autonomous vehicles.This problem has motivated significant amounts of work in the behavior prediction community on learning rich distributions of the future states and actions of agents. However, most current work on trajectory planning in the presence of uncertain agents or obstacles is limited to the case of Gaussian uncertainty with linear constraints, which is a limited representation, or requires sampling, which can be computationally intractable to encode in an optimization problem. In this paper, wepresent a general method for enforcing chance-constraints on the probability of collision with other agents in trajectory planning problems for autonomous driving that can be used with non-Gaussian mixture models of agent positions. Our method involves using statistical moments of the non-Gaussian distributions in concentration inequalities to upper bound the probability of polynomial constraint violation. In experiments,we show that the resulting optimization problem can be solved with state-of-the-art nonlinear program (NLP) solvers to plan trajectories with 5 second horizons with low latency.
- 21 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (4) , 6041-6048
Non-Gaussian Chance-Constrained Trajectory Planning for Autonomous Vehicles Under Agent Uncertainty
Agent behavior is arguably the greatest source of uncertainty in trajectory planning for autonomous vehicles.This problem has motivated significant amounts of work in the behavior prediction community on learning rich distributions of the future states and actions of agents. However, most current work on trajectory planning in the presence of uncertain agents or obstacles is limited to the case of Gaussian uncertainty with linear constraints, which is a limited representation, or requires sampling, which can be computationally intractable to encode in an optimization problem. In this paper, wepresent a general method for enforcing chance-constraints on the probability of collision with other agents in trajectory planning problems for autonomous driving that can be used with non-Gaussian mixture models of agent positions. Our method involves using statistical moments of the non-Gaussian distributions in concentration inequalities to upper bound the probability of polynomial constraint violation. In experiments,we show that the resulting optimization problem can be solved with state-of-the-art nonlinear program (NLP) solvers to plan trajectories with 5 second horizons with low latency.
- Open Access
Non-Gaussian Chance-Constrained Trajectory Planning for Autonomous Vehicles under Agent Uncertainty
Agent behavior is arguably the greatest source of uncertainty in trajectory planning for autonomous vehicles. This problem has motivated significant amounts of work in the behavior prediction community on learning rich distributions of the future states and actions of agents. However, most current works on chance-constrained trajectory planning under agent or obstacle uncertainty either assume Gaussian uncertainty or linear constraints, which is limiting, or requires sampling, which can be computationally intractable to encode in an optimization problem. In this paper, we extend the state-of-the-art by presenting a methodology to upper-bound chance-constraints defined by polynomials and mixture models with potentially non-Gaussian components. Our method achieves its generality by using statistical moments of the distributions in concentration inequalities to upper-bound the probability of constraint violation. With this method, optimization-based trajectory planners can plan trajectories that are chance-constrained with respect to a wide range of distributions representing predictions of agent future positions. In experiments, we show that the resulting optimization problem can be solved with state-of-the-art nonlinear program solvers to plan trajectories fast enough for use online.
Open AccessNon-Gaussian Chance-Constrained Trajectory Planning for Autonomous Vehicles under Agent Uncertainty
Agent behavior is arguably the greatest source of uncertainty in trajectory planning for autonomous vehicles. This problem has motivated significant amounts of work in the behavior prediction community on learning rich distributions of the future states and actions of agents. However, most current works on chance-constrained trajectory planning under agent or obstacle uncertainty either assume Gaussian uncertainty or linear constraints, which is limiting, or requires sampling, which can be computationally intractable to encode in an optimization problem. In this paper, we extend the state-of-the-art by presenting a methodology to upper-bound chance-constraints defined by polynomials and mixture models with potentially non-Gaussian components. Our method achieves its generality by using statistical moments of the distributions in concentration inequalities to upper-bound the probability of constraint violation. With this method, optimization-based trajectory planners can plan trajectories that are chance-constrained with respect to a wide range of distributions representing predictions of agent future positions. In experiments, we show that the resulting optimization problem can be solved with state-of-the-art nonlinear program solvers to plan trajectories fast enough for use online.
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-235
Robust Lane Detection with Binary Integer Optimization
Formula Student Driverless (FSD) is a competition where student teams compete to build an autonomous racecar. The main dynamic event in FSD is trackdrive, where the racecar traverses an unknown track with lanes demarcated by cones. One major challenge of the event is to determine the boundaries of the lane from cones perceived online despite false positive cone detections and sharp turns. We present a binary integer optimization to address this problem by leveraging a priori knowledge from competition rules on parameters such as average cone spacings and minimum track width. In this paper, we describe our approach, and analyze its latency, accuracy, and robustness to false positive cone detections. This approach is used on-board to solve the lane detection problem during the competition in real-time.
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-235
Robust Lane Detection with Binary Integer Optimization
Formula Student Driverless (FSD) is a competition where student teams compete to build an autonomous racecar. The main dynamic event in FSD is trackdrive, where the racecar traverses an unknown track with lanes demarcated by cones. One major challenge of the event is to determine the boundaries of the lane from cones perceived online despite false positive cone detections and sharp turns. We present a binary integer optimization to address this problem by leveraging a priori knowledge from competition rules on parameters such as average cone spacings and minimum track width. In this paper, we describe our approach, and analyze its latency, accuracy, and robustness to false positive cone detections. This approach is used on-board to solve the lane detection problem during the competition in real-time.