Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Jonathan P. How

Jonathan P. How

Massachusetts Institute of Technology

Reachability Analysis of Neural Feedback Loops


Aug 09, 2021
Michael Everett, Golnaz Habibi, Chuangchuang Sun, Jonathan P. How

Figure 1 for Reachability Analysis of Neural Feedback Loops
Figure 2 for Reachability Analysis of Neural Feedback Loops
Figure 3 for Reachability Analysis of Neural Feedback Loops
Figure 4 for Reachability Analysis of Neural Feedback Loops

  Access Paper or Ask Questions

Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems


Jun 28, 2021
Yulun Tian, Yun Chang, Fernando Herrera Arias, Carlos Nieto-Granda, Jonathan P. How, Luca Carlone

Figure 1 for Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
Figure 2 for Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
Figure 3 for Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
Figure 4 for Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
* 18 pages, 15 figures 
  Access Paper or Ask Questions

Airflow-Inertial Odometry for Resilient State Estimation on Multirotors


May 27, 2021
Andrea Tagliabue, Jonathan P. How

Figure 1 for Airflow-Inertial Odometry for Resilient State Estimation on Multirotors
Figure 2 for Airflow-Inertial Odometry for Resilient State Estimation on Multirotors
Figure 3 for Airflow-Inertial Odometry for Resilient State Estimation on Multirotors
Figure 4 for Airflow-Inertial Odometry for Resilient State Estimation on Multirotors
* Accepted to the 2021 International Conference on Robotics and Automation (ICRA 2021). Contains minor updates in Fig. 2 and Section IV.b, VII.E, VII.F 
  Access Paper or Ask Questions

NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows


May 11, 2021
Qiangqiang Huang, Can Pu, Dehann Fourie, Kasra Khosoussi, Jonathan P. How, John J. Leonard

Figure 1 for NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows
Figure 2 for NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows
Figure 3 for NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows
Figure 4 for NF-iSAM: Incremental Smoothing and Mapping via Normalizing Flows
* 8 pages, 6 figures, to be published in IEEE International Conference on Robotics and Automation (ICRA) 2021 
  Access Paper or Ask Questions

Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations


Mar 27, 2021
Stewart Jamieson, Kaveh Fathian, Kasra Khosoussi, Jonathan P. How, Yogesh Girdhar

Figure 1 for Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations
Figure 2 for Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations
Figure 3 for Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations
Figure 4 for Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations
* 7 pages, 6 figures, 1 table; accepted for presentation in IEEE Int. Conf. on Robotics and Automation, ICRA '21, Xi'an, China, June 2021 
  Access Paper or Ask Questions

PANTHER: Perception-Aware Trajectory Planner in Dynamic Environments


Mar 10, 2021
Jesus Tordesillas, Jonathan P. How

Figure 1 for PANTHER: Perception-Aware Trajectory Planner in Dynamic Environments
Figure 2 for PANTHER: Perception-Aware Trajectory Planner in Dynamic Environments
Figure 3 for PANTHER: Perception-Aware Trajectory Planner in Dynamic Environments
Figure 4 for PANTHER: Perception-Aware Trajectory Planner in Dynamic Environments
* 8 pages 
  Access Paper or Ask Questions

Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians


Feb 26, 2021
Bruno Brito, Michael Everett, Jonathan P. How, Javier Alonso-Mora

Figure 1 for Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians
Figure 2 for Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians
Figure 3 for Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians
Figure 4 for Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians
* 8 pages, 6 figures 
  Access Paper or Ask Questions

LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments


Feb 05, 2021
Andrea Tagliabue, Jesus Tordesillas, Xiaoyi Cai, Angel Santamaria-Navarro, Jonathan P. How, Luca Carlone, Ali-akbar Agha-mohammadi

Figure 1 for LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments
Figure 2 for LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments
Figure 3 for LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments
Figure 4 for LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments
* 2020 International Symposium on Experimental Robotics (ISER 2020) 
  Access Paper or Ask Questions

Non-Monotone Energy-Aware Information Gathering for Heterogeneous Robot Teams


Jan 26, 2021
Xiaoyi Cai, Brent Schlotfeldt, Kasra Khosoussi, Nikolay Atanasov, George J. Pappas, Jonathan P. How

Figure 1 for Non-Monotone Energy-Aware Information Gathering for Heterogeneous Robot Teams
Figure 2 for Non-Monotone Energy-Aware Information Gathering for Heterogeneous Robot Teams
Figure 3 for Non-Monotone Energy-Aware Information Gathering for Heterogeneous Robot Teams
Figure 4 for Non-Monotone Energy-Aware Information Gathering for Heterogeneous Robot Teams
* Submitted to ICRA'21 
  Access Paper or Ask Questions

Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllers


Jan 05, 2021
Michael Everett, Golnaz Habibi, Jonathan P. How

Figure 1 for Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllers
Figure 2 for Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllers
Figure 3 for Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllers
Figure 4 for Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllers

  Access Paper or Ask Questions

CLIPPER: A Graph-Theoretic Framework for Robust Data Association


Nov 20, 2020
Parker C. Lusk, Kaveh Fathian, Jonathan P. How

Figure 1 for CLIPPER: A Graph-Theoretic Framework for Robust Data Association
Figure 2 for CLIPPER: A Graph-Theoretic Framework for Robust Data Association
Figure 3 for CLIPPER: A Graph-Theoretic Framework for Robust Data Association
Figure 4 for CLIPPER: A Graph-Theoretic Framework for Robust Data Association

  Access Paper or Ask Questions

Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping


Nov 08, 2020
Yun Chang, Yulun Tian, Jonathan P. How, Luca Carlone

Figure 1 for Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping
Figure 2 for Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping
Figure 3 for Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping
Figure 4 for Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping
* 9 pages 
  Access Paper or Ask Questions

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning


Oct 31, 2020
Dong-Ki Kim, Miao Liu, Matthew Riemer, Chuangchuang Sun, Marwa Abdulhai, Golnaz Habibi, Sebastian Lopez-Cot, Gerald Tesauro, Jonathan P. How

Figure 1 for A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
Figure 2 for A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
Figure 3 for A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
Figure 4 for A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
* Under review as a conference paper 
  Access Paper or Ask Questions

MADER: Trajectory Planner in Multi-Agent and Dynamic Environments


Oct 21, 2020
Jesus Tordesillas, Jonathan P. How

Figure 1 for MADER: Trajectory Planner in Multi-Agent and Dynamic Environments
Figure 2 for MADER: Trajectory Planner in Multi-Agent and Dynamic Environments
Figure 3 for MADER: Trajectory Planner in Multi-Agent and Dynamic Environments
Figure 4 for MADER: Trajectory Planner in Multi-Agent and Dynamic Environments
* 14 pages, 15 figures 
  Access Paper or Ask Questions

MINVO Basis: Finding Simplexes with Minimum Volume Enclosing Polynomial Curves


Oct 21, 2020
Jesus Tordesillas, Jonathan P. How

Figure 1 for MINVO Basis: Finding Simplexes with Minimum Volume Enclosing Polynomial Curves
Figure 2 for MINVO Basis: Finding Simplexes with Minimum Volume Enclosing Polynomial Curves
Figure 3 for MINVO Basis: Finding Simplexes with Minimum Volume Enclosing Polynomial Curves
Figure 4 for MINVO Basis: Finding Simplexes with Minimum Volume Enclosing Polynomial Curves
* 17 pages, 16 figures 
  Access Paper or Ask Questions

Robustness Analysis of Neural Networks via Efficient Partitioning: Theory and Applications in Control Systems


Oct 01, 2020
Michael Everett, Golnaz Habibi, Jonathan P. How

Figure 1 for Robustness Analysis of Neural Networks via Efficient Partitioning: Theory and Applications in Control Systems
Figure 2 for Robustness Analysis of Neural Networks via Efficient Partitioning: Theory and Applications in Control Systems
Figure 3 for Robustness Analysis of Neural Networks via Efficient Partitioning: Theory and Applications in Control Systems
Figure 4 for Robustness Analysis of Neural Networks via Efficient Partitioning: Theory and Applications in Control Systems

  Access Paper or Ask Questions

Lunar Terrain Relative Navigation Using a Convolutional Neural Network for Visual Crater Detection


Jul 15, 2020
Lena M. Downes, Ted J. Steiner, Jonathan P. How

Figure 1 for Lunar Terrain Relative Navigation Using a Convolutional Neural Network for Visual Crater Detection
Figure 2 for Lunar Terrain Relative Navigation Using a Convolutional Neural Network for Visual Crater Detection
Figure 3 for Lunar Terrain Relative Navigation Using a Convolutional Neural Network for Visual Crater Detection
Figure 4 for Lunar Terrain Relative Navigation Using a Convolutional Neural Network for Visual Crater Detection
* 6 pages, 4 figures. This work was accepted by the 2020 American Control Conference 
  Access Paper or Ask Questions

Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer


Jul 09, 2020
Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How

Figure 1 for Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer
Figure 2 for Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer
Figure 3 for Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer
Figure 4 for Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer
* Accepted to ICML 2020 Workshop Theoretical Foundations of RL 
  Access Paper or Ask Questions

Collision Probabilities for Continuous-Time Systems Without Sampling [with Appendices]


Jun 01, 2020
Kristoffer M. Frey, Ted J. Steiner, Jonathan P. How

Figure 1 for Collision Probabilities for Continuous-Time Systems Without Sampling [with Appendices]
Figure 2 for Collision Probabilities for Continuous-Time Systems Without Sampling [with Appendices]
Figure 3 for Collision Probabilities for Continuous-Time Systems Without Sampling [with Appendices]
Figure 4 for Collision Probabilities for Continuous-Time Systems Without Sampling [with Appendices]
* To appear at RSS 2020 
  Access Paper or Ask Questions

Certified Adversarial Robustness for Deep Reinforcement Learning


Apr 11, 2020
Michael Everett, Bjorn Lutjens, Jonathan P. How

Figure 1 for Certified Adversarial Robustness for Deep Reinforcement Learning
Figure 2 for Certified Adversarial Robustness for Deep Reinforcement Learning
Figure 3 for Certified Adversarial Robustness for Deep Reinforcement Learning
Figure 4 for Certified Adversarial Robustness for Deep Reinforcement Learning
* arXiv admin note: text overlap with arXiv:1910.12908 
  Access Paper or Ask Questions

Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments


Mar 10, 2020
Stewart Jamieson, Jonathan P. How, Yogesh Girdhar

Figure 1 for Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
Figure 2 for Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
Figure 3 for Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
Figure 4 for Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
* 7 pages, 4 figures; accepted for presentation in IEEE Int. Conf. on Robotics and Automation, ICRA '20, Paris, France, June 2020 
  Access Paper or Ask Questions

Asynchronous and Parallel Distributed Pose Graph Optimization


Mar 06, 2020
Yulun Tian, Alec Koppel, Amrit Singh Bedi, Jonathan P. How

Figure 1 for Asynchronous and Parallel Distributed Pose Graph Optimization
Figure 2 for Asynchronous and Parallel Distributed Pose Graph Optimization
Figure 3 for Asynchronous and Parallel Distributed Pose Graph Optimization
Figure 4 for Asynchronous and Parallel Distributed Pose Graph Optimization

  Access Paper or Ask Questions

Touch the Wind: Simultaneous Airflow, Drag and Interaction Sensing on a Multirotor


Mar 04, 2020
Andrea Tagliabue, Aleix Paris, Suhan Kim, Regan Kubicek, Sarah Bergbreiter, Jonathan P. How

Figure 1 for Touch the Wind: Simultaneous Airflow, Drag and Interaction Sensing on a Multirotor
Figure 2 for Touch the Wind: Simultaneous Airflow, Drag and Interaction Sensing on a Multirotor
Figure 3 for Touch the Wind: Simultaneous Airflow, Drag and Interaction Sensing on a Multirotor
Figure 4 for Touch the Wind: Simultaneous Airflow, Drag and Interaction Sensing on a Multirotor
* The first two authors contributed equally 
  Access Paper or Ask Questions

A Distributed Pipeline for Scalable, Deconflicted Formation Flying


Mar 04, 2020
Parker C. Lusk, Xiaoyi Cai, Samir Wadhwania, Aleix Paris, Kaveh Fathian, Jonathan P. How

Figure 1 for A Distributed Pipeline for Scalable, Deconflicted Formation Flying
Figure 2 for A Distributed Pipeline for Scalable, Deconflicted Formation Flying
Figure 3 for A Distributed Pipeline for Scalable, Deconflicted Formation Flying
Figure 4 for A Distributed Pipeline for Scalable, Deconflicted Formation Flying
* 8 pages, 8 figures, submitted to 2020 IEEE IROS with IEEE RAS RA-L option 
  Access Paper or Ask Questions

Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph


Mar 03, 2020
Chuangchuang Sun, Macheng Shen, Jonathan P. How

Figure 1 for Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph
Figure 2 for Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph
Figure 3 for Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph
Figure 4 for Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph

  Access Paper or Ask Questions

R-MADDPG for Partially Observable Environments and Limited Communication


Feb 18, 2020
Rose E. Wang, Michael Everett, Jonathan P. How

Figure 1 for R-MADDPG for Partially Observable Environments and Limited Communication
Figure 2 for R-MADDPG for Partially Observable Environments and Limited Communication
Figure 3 for R-MADDPG for Partially Observable Environments and Limited Communication
Figure 4 for R-MADDPG for Partially Observable Environments and Limited Communication
* Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning, Long Beach, California, USA, 2019 
 * Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning, Long Beach, California, USA, 2019 
  Access Paper or Ask Questions

Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning


Jan 18, 2020
Samaneh Hosseini Semnani, Hugh Liu, Michael Everett, Anton de Ruiter, Jonathan P. How

Figure 1 for Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning
Figure 2 for Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning
Figure 3 for Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning
Figure 4 for Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning

  Access Paper or Ask Questions

FASTER: Fast and Safe Trajectory Planner for Flights in Unknown Environments


Jan 09, 2020
Jesus Tordesillas, Brett T. Lopez, Michael Everett, Jonathan P. How

Figure 1 for FASTER: Fast and Safe Trajectory Planner for Flights in Unknown Environments
Figure 2 for FASTER: Fast and Safe Trajectory Planner for Flights in Unknown Environments
Figure 3 for FASTER: Fast and Safe Trajectory Planner for Flights in Unknown Environments
Figure 4 for FASTER: Fast and Safe Trajectory Planner for Flights in Unknown Environments
* Journal paper. arXiv admin note: text overlap with arXiv:1903.03558 
  Access Paper or Ask Questions

Block-Coordinate Descent on the Riemannian Staircase for Certifiably Correct Distributed Rotation and Pose Synchronization


Dec 21, 2019
Yulun Tian, Kasra Khosoussi, Jonathan P. How

Figure 1 for Block-Coordinate Descent on the Riemannian Staircase for Certifiably Correct Distributed Rotation and Pose Synchronization
Figure 2 for Block-Coordinate Descent on the Riemannian Staircase for Certifiably Correct Distributed Rotation and Pose Synchronization
Figure 3 for Block-Coordinate Descent on the Riemannian Staircase for Certifiably Correct Distributed Rotation and Pose Synchronization
Figure 4 for Block-Coordinate Descent on the Riemannian Staircase for Certifiably Correct Distributed Rotation and Pose Synchronization
* technical report version 3 (add missing step in algorithm 1) 
  Access Paper or Ask Questions