cGAN surrogates recover 45-60% of CFD energy savings and high-velocity wake avoidance in 3D AUV path planning while running at 28-146 microsecond inference speeds across 19,800 trajectories.
hub
Robust task-space quadratic programming for kinematic-controlled robots.IEEE Transactions on Robotics, 39(5):3857–3874
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 2
citation-polarity summary
representative citing papers
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.
SODA uses differential algebra and adaptive Gaussian mixtures to solve chance-constrained nonlinear trajectory optimization problems for space missions with non-Gaussian uncertainties.
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 grounds discrete-time joint acceleration commands in voltage-constrained actuator physics to eliminate unrealizable accelerations and reduce oscillations in electric motor systems.
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.
Swazure enables FLS swarms to cooperatively measure relative poses for 3D point-cloud displays, achieving 100% neighbor positioning for medium FLS sizes and using Move Obstructing heuristic to resolve ~30% of obstructions in worst cases.
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.
A multi-channel terrain affordance reward combined with lower-body compliance training via virtual wrenches enables end-to-end PPO-trained humanoid policies to walk at 1 m/s on 0.2 m risers with improved payload robustness.
Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.
Zero-shot sim-to-real transfer of independently trained RL policies for cart-pole swing-up and stabilization is achieved via sensitivity-guided domain randomization, linear curriculum learning, and first-order action smoothing with Simulink switching logic.
citing papers explorer
-
3D Underwater Path Planning via Generative Flow Field Surrogates
cGAN surrogates recover 45-60% of CFD energy savings and high-velocity wake avoidance in 3D AUV path planning while running at 28-146 microsecond inference speeds across 19,800 trajectories.
-
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.
-
Non-linear stochastic trajectory optimisation
SODA uses differential algebra and adaptive Gaussian mixtures to solve chance-constrained nonlinear trajectory optimization problems for space missions with non-Gaussian uncertainties.
-
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 grounds discrete-time joint acceleration commands in voltage-constrained actuator physics to eliminate unrealizable accelerations and reduce oscillations in electric motor systems.
-
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.
-
Swazure: Swarm Measurement of Pose for Flying Light Specks
Swazure enables FLS swarms to cooperatively measure relative poses for 3D point-cloud displays, achieving 100% neighbor positioning for medium FLS sizes and using Move Obstructing heuristic to resolve ~30% of obstructions in worst cases.
-
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.
-
TACT-ful: Multi-Channel Terrain Affordance and Compliance Training for Payload-Robust Perceptive Humanoid Locomotion
A multi-channel terrain affordance reward combined with lower-body compliance training via virtual wrenches enables end-to-end PPO-trained humanoid policies to walk at 1 m/s on 0.2 m risers with improved payload robustness.
-
Adversarial Stress Testing of SPARK Humanoid Safety Filters
Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.
-
Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System
Zero-shot sim-to-real transfer of independently trained RL policies for cart-pole swing-up and stabilization is achieved via sensitivity-guided domain randomization, linear curriculum learning, and first-order action smoothing with Simulink switching logic.