no code implementations • 3 Mar 2024 • Muchen Sun, Francesca Baldini, Peter Trautman, Todd Murphey
Our framework consistently outperforms both non-learning and learning-based methods on both safety and navigation efficiency and reaches human-level crowd navigation performance on top of a meta-planner.
no code implementations • 3 Mar 2024 • Muchen Sun, Ayush Gaggar, Peter Trautman, Todd Murphey
However, current methods typically have exponential computation complexity in the search space dimension and are restricted to Euclidean space.
1 code implementation • 11 May 2023 • Taosha Fan, Joseph Ortiz, Ming Hsiao, Maurizio Monge, Jing Dong, Todd Murphey, Mustafa Mukadam
In this paper, we present a fully decentralized method that alleviates computation and communication bottlenecks to solve arbitrarily large bundle adjustment problems.
1 code implementation • 26 Sep 2022 • Muchen Sun, Allison Pinosky, Ian Abraham, Todd Murphey
Functional registration algorithms represent point clouds as functions (e. g. spacial occupancy field) avoiding unreliable correspondence estimation in conventional least-squares registration algorithms.
no code implementations • ICCV 2021 • Taosha Fan, Kalyan Vasudev Alwala, Donglai Xiang, Weipeng Xu, Todd Murphey, Mustafa Mukadam
We propose a novel sparse constrained formulation and from it derive a real-time optimization method for 3D human pose and shape estimation.
no code implementations • 4 Dec 2020 • Taosha Fan, Todd Murphey
In this paper, we generalize proximal methods that were originally designed for convex optimization on normed vector space to non-convex pose graph optimization (PGO) on special Euclidean groups, and show that our proposed generalized proximal methods for PGO converge to first-order critical points.
Simultaneous Localization and Mapping Optimization and Control Robotics
1 code implementation • 25 Jun 2020 • Taosha Fan, Hanlin Wang, Michael Rubenstein, Todd Murphey
In this paper, we consider the problem of planar graph-based simultaneous localization and mapping (SLAM) that involves both poses of the autonomous agent and positions of observed landmarks.
1 code implementation • 12 Jun 2020 • Alexander Broad, Ian Abraham, Todd Murphey, Brenna Argall
Overall, we find that model-based shared control significantly improves task and control metrics when compared to a natural learning, or user only, control paradigm.
no code implementations • 11 Mar 2020 • Taosha Fan, Todd Murphey
In this paper, we consider the problem of distributed pose graph optimization (PGO) that has extensive applications in multi-robot simultaneous localization and mapping (SLAM).
1 code implementation • 5 Jun 2019 • Alexander Broad, Todd Murphey, Brenna Argall
In this paradigm, the role of the autonomous partner is to improve the general safety of the system without constraining the user's ability to achieve unspecified behaviors.
1 code implementation • 24 Aug 2018 • Alexander Broad, Todd Murphey, Brenna Argall
We present a novel approach to shared control of human-machine systems.
no code implementations • 3 Aug 2018 • Alexander Broad, Ian Abraham, Todd Murphey, Brenna Argall
We present a structured neural network architecture that is inspired by linear time-varying dynamical systems.
no code implementations • 12 Sep 2017 • Gerardo De La Torre, Todd Murphey
In this paper, we introduce a new class of variational integrators that achieve fourth-order convergence despite having the same integration scheme as traditional second-order variational integrators.
Numerical Analysis
no code implementations • 8 Sep 2017 • Ahalya Prabhakar, Anastasia Mavrommati, Jarvis Schultz, Todd Murphey
This paper addresses the problem of enabling a robot to represent and recreate visual information through physical motion, focusing on drawing using pens, brushes, or other tools.
Robotics
no code implementations • 7 Sep 2017 • Vlad Seghete, Todd Murphey
This paper presents existence and uniqueness results for a propagative model of simultaneous impacts that is guaranteed to conserve energy and momentum in the case of elastic impacts with extensions to perfectly plastic and inelastic impacts.
Robotics