Publications

Meridian: Metric-Semantic Primitive Matching for Cross-View Geo-Localization Beyond Urban Environments

Mason Peterson, Qingyuan Li, Yixuan Jia, Fernando Cladera, Carlos Nieto-Granda, Camillo Jose Taylor, Jonathan P. How

arXiv preprint, 2026

Paper Code Cite

Meridian: Metric-Semantic Primitive Matching for Cross-View Geo-Localization Beyond Urban Environments

Mason Peterson, Qingyuan Li, Yixuan Jia, Fernando Cladera, Carlos Nieto-Granda, Camillo Jose Taylor, Jonathan P. How

arXiv preprint, 2026

Successful robot automation requires accurate global localization to support repeatability, task planning, goal specification, and safe operation. However, reliable localization in GNSS-denied environments remains an open problem. Overhead aerial imagery offers a promising solution, but existing approaches primarily target structured urban environments and have been rarely demonstrated in unstructured natural terrain. Limitations of the state-of-the-art include a reliance on models trained for specific environments, as well as difficulty handling repetitive geometries and featureless landscapes commonly found in natural outdoor areas. To overcome these challenges, we present Meridian, a method for matching high-level metric-semantic primitives across aerial images and ground robot RGB-D camera data that achieves accurate global localization and generalizes well across diverse environments, all without any training or algorithmic fine-tuning on area-specific data. We formulate novel consistency metrics to estimate a distribution over robot submap poses and to reject outlier hypotheses in a robust pose graph optimization step for accurate robot trajectory estimation. We demonstrate that our algorithm can localize a ground robot across a wide variety of environments, including an autonomous driving dataset, a park and campus area, and a wilderness camp, with an average optimized trajectory error of 2.4 m over 19 km of ground traversal.

Paper Code

ROMAN: Open-Set Object Map Alignment for Robust View-Invariant Global Localization

Mason Peterson, Yixuan Jia, Yulun Tian, Annika Thomas, Jonathan P. How

Robotics: Science and Systems (RSS), 2025

Paper Code Website Cite

ROMAN: Open-Set Object Map Alignment for Robust View-Invariant Global Localization

Mason Peterson, Yixuan Jia, Yulun Tian, Annika Thomas, Jonathan P. How

Robotics: Science and Systems (RSS), 2025

Global localization is a fundamental capability required for long-term and drift-free robot navigation. However, current methods fail to relocalize when faced with significantly different viewpoints. We present ROMAN (Robust Object Map Alignment Anywhere), a global localization method capable of localizing in challenging and diverse environments by creating and aligning maps of open-set and view-invariant objects. ROMAN formulates and solves a registration problem between object submaps using a unified graph-theoretic global data association approach with a novel incorporation of a gravity direction prior and object shape and semantic similarity. This work's open-set object mapping and information-rich object association algorithm enables global localization, even in instances when maps are created from robots traveling in opposite directions. Through a set of challenging global localization experiments in indoor, urban, and unstructured/forested environments, we demonstrate that ROMAN achieves higher relative pose estimation accuracy than other image-based pose estimation methods or segment-based registration methods. Additionally, we evaluate ROMAN as a loop closure module in large-scale multi-robot SLAM and show a 35% improvement in trajectory estimation error compared to standard SLAM systems using visual features for loop closures.

Paper Code Website

TCAFF: Temporal Consistency for Robot Frame Alignment

Mason Peterson, Parker C. Lusk, Antonio Avila, Jonathan P. How

IEEE International Conference on Robotics and Automation (ICRA), 2025

Paper Code Cite

TCAFF: Temporal Consistency for Robot Frame Alignment

Mason Peterson, Parker C. Lusk, Antonio Avila, Jonathan P. How

IEEE International Conference on Robotics and Automation (ICRA), 2025

In the field of collaborative robotics, the ability to communicate spatial information like planned trajectories and shared environment information is crucial. When no global position information is available (e.g., indoor or GPS-denied environments), agents must align their coordinate frames before shared spatial information can be properly expressed and interpreted. Coordinate frame alignment is particularly difficult when robots have no initial alignment and are affected by odometry drift. To this end, we develop a novel multiple hypothesis algorithm, called TCAFF, for aligning the coordinate frames of neighboring robots. TCAFF considers potential alignments from associating sparse open-set object maps and leverages temporal consistency to determine an initial alignment and correct for drift, all without any initial knowledge of neighboring robot poses. We demonstrate TCAFF being used for frame alignment in a collaborative object tracking application on a team of four robots tracking six pedestrians and show that TCAFF enables robots to achieve a tracking accuracy similar to that of a system with ground truth localization. The code and hardware dataset are available at https://github.com/mit-acl/tcaff.

Paper Code

MOTLEE: Distributed Mobile Multi-Object Tracking with Localization Error Elimination

Mason Peterson, Parker C. Lusk, Jonathan P. How

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

Paper Code Cite

MOTLEE: Distributed Mobile Multi-Object Tracking with Localization Error Elimination

Mason Peterson, Parker C. Lusk, Jonathan P. How

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

We present MOTLEE, a distributed mobile multi-object tracking algorithm that enables a team of robots to collaboratively track moving objects in the presence of localization error. Existing approaches to distributed tracking make limiting assumptions regarding the relative spatial relationship of sensors, including assuming a static sensor network or that perfect localization is available. Instead, we develop an algorithm based on the Kalman-Consensus filter for distributed tracking that properly leverages localization uncertainty in collaborative tracking. Further, our method allows the team to maintain an accurate understanding of dynamic objects in the environment by realigning robot frames and incorporating frame alignment uncertainty into our object tracking formulation. We evaluate our method in hardware on a team of three mobile ground robots tracking four people. Compared to previous works that do not account for localization error, we show that MOTLEE is resilient to localization uncertainties, enabling accurate tracking in distributed, dynamic settings with mobile tracking sensors.

Paper Code

Theses

Relative Robot Localization and Frame Alignment for Multi-Robot Collaboration

Mason Peterson

SM Thesis, 2024

MIT Department of Aeronautics and Astronautics

Paper Cite

Relative Robot Localization and Frame Alignment for Multi-Robot Collaboration

Mason Peterson

SM Thesis, MIT Department of Aeronautics and Astronautics, 2024

The growing field of collaborative robotics has the potential to enable and improve the execution of many challenging robot applications. For instance, with teamwork between multiple agents, dynamic object tracking can more completely cover an environment and trajectory planning becomes safer. However, for robots to share the quickly changing spatial information involved in these tasks, robots need to be able to express information originally sensed or planned in their own frame into the frame of neighboring agents. This can be challenging in cases where robots have no global pose information resulting in steady accumulation of error, or drift, in their local pose estimates. To mitigate the effects of drift, neighboring agents must make up-to-date estimates of the alignment between their frames, which can be difficult due to ambiguous alignments and the presence of outlier measurements. To address these issues, the first contribution of this thesis is a method for performing fast incremental frame alignment between pairs of robots, enabling collaborative multiple object tracking (MOT), the task of monitoring the locations of dynamic objects in an environment. To perform frame alignment, robots build up maps of recently seen static objects and use these maps and the detections of tracked dynamic objects to correct for frame drift. Using frame alignment estimates, agents share object detection information and account for additional uncertainty associated with the alignment estimate. The second contribution of this thesis presents a method to perform frame alignment with no initial guess. Many potential frame alignments are computed and we develop a filter that uses temporal consistency to reject outlier alignments and only accept a series of alignments that are consistent over time. We demonstrate in hardware experiments our ability to perform frame alignment in difficult scenarios and improve the quality of collaborative object tracking onboard real robots.

Paper