Alert button
Picture for Matthew Anderson

Matthew Anderson

Alert button

Online Self-Supervised Thermal Water Segmentation for Aerial Vehicles

Jul 18, 2023
Connor Lee, Jonathan Gustafsson Frennert, Lu Gan, Matthew Anderson, Soon-Jo Chung

We present a new method to adapt an RGB-trained water segmentation network to target-domain aerial thermal imagery using online self-supervision by leveraging texture and motion cues as supervisory signals. This new thermal capability enables current autonomous aerial robots operating in near-shore environments to perform tasks such as visual navigation, bathymetry, and flow tracking at night. Our method overcomes the problem of scarce and difficult-to-obtain near-shore thermal data that prevents the application of conventional supervised and unsupervised methods. In this work, we curate the first aerial thermal near-shore dataset, show that our approach outperforms fully-supervised segmentation models trained on limited target-domain thermal data, and demonstrate real-time capabilities onboard an Nvidia Jetson embedded computing platform. Code and datasets used in this work will be available at: https://github.com/connorlee77/uav-thermal-water-segmentation.

* 8 pages, 4 figures, 3 tables 
Viaarxiv icon

Efficiently-Verifiable Strong Uniquely Solvable Puzzles and Matrix Multiplication

Jul 12, 2023
Matthew Anderson, Vu Le

Figure 1 for Efficiently-Verifiable Strong Uniquely Solvable Puzzles and Matrix Multiplication
Figure 2 for Efficiently-Verifiable Strong Uniquely Solvable Puzzles and Matrix Multiplication

We advance the Cohn-Umans framework for developing fast matrix multiplication algorithms. We introduce, analyze, and search for a new subclass of strong uniquely solvable puzzles (SUSP), which we call simplifiable SUSPs. We show that these puzzles are efficiently verifiable, which remains an open question for general SUSPs. We also show that individual simplifiable SUSPs can achieve the same strength of bounds on the matrix multiplication exponent $\omega$ that infinite families of SUSPs can. We report on the construction, by computer search, of larger SUSPs than previously known for small width. This, combined with our tighter analysis, strengthens the upper bound on the matrix multiplication exponent from $2.66$ to $2.505$ obtainable via this computational approach, and nears the results of the handcrafted constructions of Cohn et al.

* 21 pages, 1 figure, 1 table 
Viaarxiv icon

Matrix Multiplication: Verifying Strong Uniquely Solvable Puzzles

Dec 30, 2022
Matthew Anderson, Zongliang Ji, Anthony Yang Xu

Cohn and Umans proposed a framework for developing fast matrix multiplication algorithms based on the embedding computation in certain groups algebras. In subsequent work with Kleinberg and Szegedy, they connected this to the search for combinatorial objects called strong uniquely solvable puzzles (strong USPs). We begin a systematic computer-aided search for these objects. We develop and implement constraint-based algorithms build on reductions to $\mathrm{SAT}$ and $\mathrm{IP}$ to verify that puzzles are strong USPs, and to search for large strong USPs. We produce tight bounds on the maximum size of a strong USP for width $k \le 5$, construct puzzles of small width that are larger than previous work, and improve the upper bounds on strong USP size for $k \le 12$. Although our work only deals with puzzles of small-constant width, the strong USPs we find imply matrix multiplication algorithms that run in $O(n^\omega)$ time with exponent $\omega \le 2.66$. While our algorithms do not beat the fastest algorithms, our work provides evidence and, perhaps, a path to finding families of strong USPs that imply matrix multiplication algorithms that are more efficient than those currently known.

* 35 pages, 7 figures, full version of SAT 2020 extended abstract 
Viaarxiv icon

Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments

Apr 20, 2021
Benjamin Riviere, Wolfgang Hoenig, Matthew Anderson, Soon-Jo Chung

Figure 1 for Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments
Figure 2 for Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments
Figure 3 for Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments
Figure 4 for Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments

We present a self-improving, neural tree expansion method for multi-robot online planning in non-cooperative environments, where each robot tries to maximize its cumulative reward while interacting with other self-interested robots. Our algorithm adapts the centralized, perfect information, discrete-action space method from Alpha Zero to a decentralized, partial information, continuous action space setting for multi-robot applications. Our method has three interacting components: (i) a centralized, perfect-information `expert' Monte Carlo Tree Search (MCTS) with large computation resources that provides expert demonstrations, (ii) a decentralized, partial-information `learner' MCTS with small computation resources that runs in real-time and provides self-play examples, and (iii) policy & value neural networks that are trained with the expert demonstrations and bias both the expert and the learner tree growth. Our numerical experiments demonstrate neural expansion generates compact search trees with better solution quality and 20 times less computational expense compared to MCTS without neural expansion. The resulting policies are dynamically sophisticated, demonstrate coordination between robots, and play the Reach-Target-Avoid differential game significantly better than the state-of-the-art control-theoretic baseline for multi-robot, double-integrator systems. Our hardware experiments on an aerial swarm demonstrate the computational advantage of neural tree expansion, enabling online planning at 20Hz with effective policies in complex scenarios.

Viaarxiv icon

NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge

Mar 28, 2021
Ali Agha, Kyohei Otsu, Benjamin Morrell, David D. Fan, Rohan Thakker, Angel Santamaria-Navarro, Sung-Kyun Kim, Amanda Bouman, Xianmei Lei, Jeffrey Edlund, Muhammad Fadhil Ginting, Kamak Ebadi, Matthew Anderson, Torkom Pailevanian, Edward Terry, Michael Wolf, Andrea Tagliabue, Tiago Stegun Vaquero, Matteo Palieri, Scott Tepsuporn, Yun Chang, Arash Kalantari, Fernando Chavez, Brett Lopez, Nobuhiro Funabiki, Gregory Miles, Thomas Touma, Alessandro Buscicchio, Jesus Tordesillas, Nikhilesh Alatur, Jeremy Nash, William Walsh, Sunggoo Jung, Hanseob Lee, Christoforos Kanellakis, John Mayo, Scott Harper, Marcel Kaufmann, Anushri Dixit, Gustavo Correa, Carlyn Lee, Jay Gao, Gene Merewether, Jairo Maldonado-Contreras, Gautam Salhotra, Maira Saboia Da Silva, Benjamin Ramtoula, Yuki Kubo, Seyed Fakoorian, Alexander Hatteland, Taeyeon Kim, Tara Bartlett, Alex Stephens, Leon Kim, Chuck Bergh, Eric Heiden, Thomas Lew, Abhishek Cauligi, Tristan Heywood, Andrew Kramer, Henry A. Leopold, Chris Choi, Shreyansh Daftry, Olivier Toupet, Inhwan Wee, Abhishek Thakur, Micah Feras, Giovanni Beltrame, George Nikolakopoulos, David Shim, Luca Carlone, Joel Burdick

Figure 1 for NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge
Figure 2 for NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge
Figure 3 for NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge
Figure 4 for NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge

This paper presents and discusses algorithms, hardware, and software architecture developed by the TEAM CoSTAR (Collaborative SubTerranean Autonomous Robots), competing in the DARPA Subterranean Challenge. Specifically, it presents the techniques utilized within the Tunnel (2019) and Urban (2020) competitions, where CoSTAR achieved 2nd and 1st place, respectively. We also discuss CoSTAR's demonstrations in Martian-analog surface and subsurface (lava tubes) exploration. The paper introduces our autonomy solution, referred to as NeBula (Networked Belief-aware Perceptual Autonomy). NeBula is an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states). We discuss various components of the NeBula framework, including: (i) geometric and semantic environment mapping; (ii) a multi-modal positioning system; (iii) traversability analysis and local planning; (iv) global motion planning and exploration behavior; (i) risk-aware mission planning; (vi) networking and decentralized reasoning; and (vii) learning-enabled adaptation. We discuss the performance of NeBula on several robot types (e.g. wheeled, legged, flying), in various environments. We discuss the specific results and lessons learned from fielding this solution in the challenging courses of the DARPA Subterranean Challenge competition.

* For team website, see https://costar.jpl.nasa.gov/ 
Viaarxiv icon

Design and Autonomous Stabilization of a Ballistically Launched Multirotor

Nov 22, 2019
Amanda Bouman, Paul Nadan, Matthew Anderson, Daniel Pastor, Jacob Izraelevitz, Joel Burdick, Brett Kennedy

Figure 1 for Design and Autonomous Stabilization of a Ballistically Launched Multirotor
Figure 2 for Design and Autonomous Stabilization of a Ballistically Launched Multirotor
Figure 3 for Design and Autonomous Stabilization of a Ballistically Launched Multirotor
Figure 4 for Design and Autonomous Stabilization of a Ballistically Launched Multirotor

Aircraft that can launch ballistically and then convert to autonomous, free flying drones have applications in many areas, such as emergency response, defense, and space exploration, where they can gather critical situational data using onboard sensors. In previous work, we presented a proof of concept, manually stabilized folding multirotor that deploys from a pressurized tube mounted on a vehicle moving at speeds of up to 50 mph. This paper presents a larger, autonomously stabilizing multirotor prototype with an onboard sensor suite, autonomy pipeline, and improved aerodynamic stability margin. We also demonstrate autonomous transition from passive to active stabilization, confirming the ability of the multirotor to autonomously stabilize after a ballistic launch in a GPS denied environment.

* Submitted to 2020 International Conference on Robotics and Automation (currently under review) 
Viaarxiv icon

Independent Vector Analysis: Identification Conditions and Performance Bounds

Mar 29, 2013
Matthew Anderson, Geng-Shen Fu, Ronald Phlypo, Tülay Adalı

Figure 1 for Independent Vector Analysis: Identification Conditions and Performance Bounds
Figure 2 for Independent Vector Analysis: Identification Conditions and Performance Bounds
Figure 3 for Independent Vector Analysis: Identification Conditions and Performance Bounds
Figure 4 for Independent Vector Analysis: Identification Conditions and Performance Bounds

Recently, an extension of independent component analysis (ICA) from one to multiple datasets, termed independent vector analysis (IVA), has been the subject of significant research interest. IVA has also been shown to be a generalization of Hotelling's canonical correlation analysis. In this paper, we provide the identification conditions for a general IVA formulation, which accounts for linear, nonlinear, and sample-to-sample dependencies. The identification conditions are a generalization of previous results for ICA and for IVA when samples are independently and identically distributed. Furthermore, a principal aim of IVA is the identification of dependent sources between datasets. Thus, we provide the additional conditions for when the arbitrary ordering of the sources within each dataset is common. Performance bounds in terms of the Cramer-Rao lower bound are also provided for the demixing matrices and interference to source ratio. The performance of two IVA algorithms are compared to the theoretical bounds.

* 14 pages, 5 figures, in review for IEEE Trans. on Signal Processing 
Viaarxiv icon