The paper introduces diagnostic certificates that separately assess state-space coverage, lifted-feature nondegeneracy, and regression-spectrum quality for Koopman and EDMDc identification, with theoretical guarantees on the smallest singular value under a population spectral gap.
Generalized multispeed dubins motion model
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
UMI enables zero-shot deployment of robot manipulation policies trained solely on portable human demonstrations captured with custom handheld grippers, supporting dynamic bimanual tasks across novel environments and objects.
SID achieves approximately 90% success on six real-world manipulation tasks with only two demonstrations under out-of-distribution initializations, with less than 10% performance drop under distractors and disturbances.
VRA is a new acceleration interface that grounds discrete-time joint commands in voltage-constrained electric actuator physics to ensure realizability.
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
PECMAN lets multiple robots share perception and morph their individual RRT* trees to replan paths in unknown environments, reducing team completion time by up to 52 percent with near-100 percent success in 28,000 simulations and real-robot tests.
citing papers explorer
-
Diagnostic Certificates of Data Quality and Regression Identifiability for Koopman Identification
The paper introduces diagnostic certificates that separately assess state-space coverage, lifted-feature nondegeneracy, and regression-spectrum quality for Koopman and EDMDc identification, with theoretical guarantees on the smallest singular value under a population spectral gap.
-
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
UMI enables zero-shot deployment of robot manipulation policies trained solely on portable human demonstrations captured with custom handheld grippers, supporting dynamic bimanual tasks across novel environments and objects.
-
SID: Sliding into Distribution for Robust Few-Demonstration Manipulation
SID achieves approximately 90% success on six real-world manipulation tasks with only two demonstrations under out-of-distribution initializations, with less than 10% performance drop under distractors and disturbances.
-
VRA: Grounding Discrete-Time Joint Acceleration in Voltage-Constrained Actuation
VRA is a new acceleration interface that grounds discrete-time joint commands in voltage-constrained electric actuator physics to ensure realizability.
-
Continuum Robot Modeling with Action Conditioned Flow Matching
A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.
-
PECMAN: Perception-enabled Collaborative Multi-Agent Navigation in Unknown Environments
PECMAN lets multiple robots share perception and morph their individual RRT* trees to replan paths in unknown environments, reducing team completion time by up to 52 percent with near-100 percent success in 28,000 simulations and real-robot tests.