Real-time, guaranteed safe trajectory planning is vital for navigation in unknown environments. However, real-time navigation algorithms typically sacrifice robustness for computation speed. Alternatively, provably sa...
详细信息
Real-time, guaranteed safe trajectory planning is vital for navigation in unknown environments. However, real-time navigation algorithms typically sacrifice robustness for computation speed. Alternatively, provably sa...
详细信息
The Koopman operator has recently garnered much attention for its value in dynamicalsystems analysis and data-driven model discovery. However, its application has been hindered by the computational complexity of exte...
详细信息
ISBN:
(纸本)9781538679012;9781538679265
The Koopman operator has recently garnered much attention for its value in dynamicalsystems analysis and data-driven model discovery. However, its application has been hindered by the computational complexity of extended dynamic mode decomposition;this requires a combinatorially large basis set to adequately describe many nonlinear systems of interest, e.g. cyber-physical infrastructure systems, biological networks, social systems, and fluid dynamics. Often the dictionaries generated for these problems are manually curated, requiring domain-specific knowledge and painstaking tuning. In this paper we introduce a computational framework for learning Koopman operators of nonlinear dynamicalsystems using deep learning. We show that this novel method automatically selects efficient deep dictionaries, requiring much lower dimensional dictionaries while outperforming state-of-the-art methods. We benchmark this method on partially observed nonlinear systems, including the glycolytic oscillator and show it is able to predict on test data quantitatively 100 steps into the future, using only a single timepoint as an initial condition, and quantitative oscillatory behavior 400 steps into the future.
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We ...
详细信息
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad
Andy Packard, an expert from University of California at Berkeley (UCB) Mechanical Engineering Department shares views on the use of sum-of-squares (SOS) methods to determine the region of attraction (ROA). SOS applie...
详细信息
Andy Packard, an expert from University of California at Berkeley (UCB) Mechanical Engineering Department shares views on the use of sum-of-squares (SOS) methods to determine the region of attraction (ROA). SOS applies to polynomials in several real variables and a polynomial is a finite linear combination of monomials. The ROA can be visualized by simulating the system from many initial conditions and plotting the trajectories in a phase plane plot for systems with two or three states. SOS techniques can be used to perform nonlinear analyses, including computation of input/output gains, estimation of reachable sets, and computation of robustness margins. The approaches that apply to SOS methods includes the computational requirements that grow rapidly in the number of variables and polynomial degree, which roughly limits SOS-based analysis to systems with at most eight to ten states, one to two inputs, and polynomial vector fields of degree 3.
In this issue of IEEE controlsystems Magazine, Andy Packard and friends respond to a query on determining the region of attraction using sum-of-squares methods.
In this issue of IEEE controlsystems Magazine, Andy Packard and friends respond to a query on determining the region of attraction using sum-of-squares methods.
Auditory localization behavior in barn owls is mediated by the integration of topographically encoded visual and auditory space maps. In juvenile owls, disruption of the audio-visual map alignment by exposure to spect...
详细信息
ISBN:
(纸本)0780390482
Auditory localization behavior in barn owls is mediated by the integration of topographically encoded visual and auditory space maps. In juvenile owls, disruption of the audio-visual map alignment by exposure to spectacles that laterally shift the visual input results in behavioral adaptation over the course of several weeks. It has been reported in literature that this adaptation is produced by architectural plasticity in the neural circuits encoding the space maps. It is known that this plasticity is guided by visual input in a topographic manner, and that the error signal is embedded in the firing dynamics of neurons in the inferior colliculus. In this work, we use leaky integrateand-fire neurons to model the key elements in the auditory localization circuit of barn owls. We demonstrate that a Hebbian spike-time dependent learning rule, coupled with an activity-dependent mechanism that promotes growth, can account for the essentials of circuit-level plasticity associated with prism experience. We point out the importance of inhibition in both the normal functioning of this circuit, and prism-induced plasticity, and comment on potential mechanisms for activity-induced growth.
Auditory localization behavior in barn owls is mediated by the integration of topographically encoded visual and auditory space maps. In juvenile owls, disruption of the audio visual map alignment by exposure to spect...
详细信息
Auditory localization behavior in barn owls is mediated by the integration of topographically encoded visual and auditory space maps. In juvenile owls, disruption of the audio visual map alignment by exposure to spectacles that laterally shift the visual input results in behavioral adaptation over the course of several weeks. It has been reported in literature that this adaptation is produced by architectural plasticity in the neural circuits encoding the space maps. It is known that this plasticity is guided by visual input in a topographic manner, and that the error signal is embedded in the firing dynamics of neurons in the inferior colliculus. In this work, we use leaky integrate-and-fire neurons to model the key elements in the auditory localization circuit of barn owls. We demonstrate that a Hebbian spike time dependent learning rule, coupled with an activity-dependent mechanism that promotes growth, can account for the essentials of circuit level plasticity associated with prism experience. We point out the importance of inhibition in both the normal functioning of this circuit, and prism induced plasticity, and comment on potential mechanisms for activity induced growth.
B. D. Coller, P. Holmes, John Lumley; Erratum: ‘‘Interaction of adjacent bursts in the wall region’’ [Phys. Fluids 6, 954 (1994)], Physics of Fluids, Volume 9,
B. D. Coller, P. Holmes, John Lumley; Erratum: ‘‘Interaction of adjacent bursts in the wall region’’ [Phys. Fluids 6, 954 (1994)], Physics of Fluids, Volume 9,
Dynamic walking on bipedal robots has evolved from an idea in science fiction to a practical reality. This is due to continued progress in three key areas: a mathematical understanding of locomotion, the computational...
Dynamic walking on bipedal robots has evolved from an idea in science fiction to a practical reality. This is due to continued progress in three key areas: a mathematical understanding of locomotion, the computational ability to encode this mathematics through optimization, and the hardware capable of realizing this understanding in practice. In this context, this review outlines the end-to-end process of methods that have proven effective in the literature for achieving dynamic walking on bipedal robots. We begin by introducing mathematical models of locomotion, from reduced-order models that capture essential walking behaviors to hybrid dynamicalsystems that encode the full-order continuous dynamics along with discrete foot-strike dynamics. These models form the basis for gait generation via (nonlinear) optimization problems. Finally, models and their generated gaits merge in the context of real-time control, wherein walking behaviors are translated to hardware. The concepts presented are illustrated throughout in simulation, and experimental instantiations on multiple walking platforms are highlighted to demonstrate the ability to realize dynamic walking on bipedal robots that is both agile and efficient.
暂无评论