Projects & Teams

Issues:

• SOTA perception algorithms have error rates that are higher than what is acceptable for safe autonomy

• SOTA lacks robustness to erroneous/outlier data found in practice

• Many algorithms cannot be used in practice due to their high computational complexity and lack of scalability

Our solutions & research plans:

• Multi-way & multi-modal inference, addressing the shortcomings of a single sensor modality 

• Algorithmic frameworks for robust data association and outlier rejection (robust to >99% outliers) 

• Fast & certifiable perception algorithms 

P. Lusk, K. Fathian, J. How, "CLIPPER: A Graph-Theoretic Framework for Robust Data Association," IEEE International Conference on Robotics and Automation, 2021, Xian, China.

P. Lusk, K. Fathian, J. P. How, “MIXER: Multiattribute, Multiway Fusion of Uncertain Pairwise Affinities,” IEEE Robotics and Automation Letters, 2022.

K. Fathian, K. Khosoussi, Y. Tian, P. Lusk, J. How, “CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multi-View Data Association,” IEEE Transactions on Robotics, 2020.

Issues: Standard Simultaneous Localization and Mapping (SLAM) pipelines lack robustness to

• Viewpoint variations (opposite views, air-ground) 

• Changing or dynamic environments

• Off-nominal conditions (bad weather, sensing failures)

Our solutions & research plans:

• View-invariant semantic & topological representations 

• Integration of SLAM and modern outlier rejection techniques to create robustness to environment changes, sensing failures, noisy and out-of-distribution data, etc.  

J. Ankenbauer, K. Fathian, J. How, "View-Invariant Localization using Semantic Objects in Changing Environments," arXiv:2209.14426, 2023.

Issues: The Internet of Robotic Things (IoRT) is a new field with challenges such as

• Limited communication budget

• Lack of global knowledge (distributed computing)

• Adversarial agents/data

Our solutions & research plans:

• IoRT on 4G/5G cellular networks

• Mixed edge & cloud computing (“fog computing”)

• Distributed learning, perception, planning, control 

• Adversary-resilient multi-agent optimization

P. Lusk, X. Cai, S. Wadhwania, A. Paris, K. Fathian, J. How “A Distributed Pipeline for Scalable, Deconflicted Formation Flying,”  IEEE Robotics and Automation Letters, 2020.

K. Fathian, S. Safaoui, T. H. Summers, N. R. Gans, “Robust Distributed Planar Formation Control for Higher-Order Holonomic and Nonholonomic Agents”  IEEE Transactions on Robotics, 2020.

Issues: Standalone perception or planning algorithms do not consider closed-loop behavior

• Planned trajectory may block camera view

• Planner does not consider perception uncertainty 

Our solutions & research plans:

• Coupled perception-planning-control algorithms (e.g., perception-aware planning)

• Active, multi-robot SLAM

• Fast C++ implementations, ROS packages, & field robotic experiments