Author name cluster

Michael Noseworthy

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ICML Conference 2025 Conference Paper

Flow-based Domain Randomization for Learning and Sequencing Robotic Skills

Aidan Curtis
Eric Li
Michael Noseworthy
Nishad Gothoskar
Sachin Chitta
Hui Li
Leslie Pack Kaelbling
Nicole E. Carey

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies learned in simulation. By randomizing properties of the environment during training, the learned policy can be robust to uncertainty along the randomized dimensions. While the environment distribution is typically specified by hand, in this paper we investigate the problem of automatically discovering this sampling distribution via entropy-regularized reward maximization of a neural sampling distribution in the form of a normalizing flow. We show that this architecture is more flexible and results in better robustness than existing approaches to learning simple parameterized sampling distributions. We demonstrate that these policies can be used to learn robust policies for contact-rich assembly tasks. Additionally, we explore how these sampling distributions, in combination with a privileged value function, can be used for out-of-distribution detection in the context of an uncertainty-aware multi-step manipulation planner.

Details

ICRA Conference 2024 Conference Paper

Amortized Inference for Efficient Grasp Model Adaptation

Michael Noseworthy
Seiji Shaw
Chad C. Kessens
Nicholas Roy

In robotic applications such as bin-picking or block-stacking, learned predictive models have been developed for manipulation of objects with varying but known dynamic properties (e. g. , mass distributions and friction coefficients). When a robot encounters a new object, these properties are often difficult to observe and must be inferred through interaction, which can be expensive in both inference time and number of interactions. We propose an encoder/decoder action-feasibility model to efficiently adapt to new objects by estimating their unobserved properties through interaction. The encoder predicts a distribution over the unobserved parameters while the decoder predicts action feasibility, which can be used in an uncertainty-aware planner. An explicit representation of uncertainty in the encoder enables information-gathering heuristics to minimize adaptation interactions. The amortized distributions are efficient to compute and perform comparably to particle-based distributions in a grasping domain. Finally, we deploy our method on a Panda robot to grasp heavy objects.

Details

ICRA Conference 2020 Conference Paper

Visual Prediction of Priors for Articulated Object Interaction

Caris Moses
Michael Noseworthy
Leslie Pack Kaelbling
Tomás Lozano-Pérez
Nicholas Roy

Exploration in novel settings can be challenging without prior experience in similar domains. However, humans are able to build on prior experience quickly and efficiently. Children exhibit this behavior when playing with toys. For example, given a toy with a yellow and blue door, a child will explore with no clear objective, but once they have discovered how to open the yellow door, they will most likely be able to open the blue door much faster. Adults also exhibit this behaviour when entering new spaces such as kitchens. We develop a method, Contextual Prior Prediction, which provides a means of transferring knowledge between interactions in similar domains through vision. We develop agents that exhibit exploratory behavior with increasing efficiency, by learning visual features that are shared across environments, and how they correlate to actions. Our problem is formulated as a Contextual Multi-Armed Bandit where the contexts are images, and the robot has access to a parameterized action space. Given a novel object, the objective is to maximize reward with few interactions. A domain which strongly exhibits correlations between visual features and motion is kinemetically constrained mechanisms. We evaluate our method on simulated prismatic and revolute joints 1.

Details

RLDM Conference 2019 Conference Abstract

Joint Goal and Constraint Inference using Bayesian Nonparametric Inverse Reinforcement Learning

Daehyung Park
Michael Noseworthy
Rohan Paul
Subhro Roy
Nicholas Roy

Inverse Reinforcement Learning (IRL) aims to recover an unknown reward function from expert demonstrations of a task. Often, the reward function fails to capture a complex behavior (e. g. , a condi- tion or a constraint) due to the simple structure of the global reward function. We introduce an algorithm, Constraint-based Bayesian Non-Parametric Inverse Reinforcement Learning (CBN-IRL), that instead repre- sents a task as a sequence of subtasks, each consisting of a goal and set of constraints, by partitioning a single demonstration into individual trajectory segments. CBN-IRL is able to find locally consistent constraints and adapt the number of subtasks according to the complexity of the demonstration using a computationally efficient inference process. We evaluate the proposed framework on two-dimensional simulation environ- ments. The results show our framework outperforms state-of-the-art IRL on a complex demonstration. We also show we can adapt the learned subgoals and constraints to randomized test environments given a single demonstration.

PDF Details

YNIMG Journal 2006 Journal Article

White matter growth as a mechanism of cognitive development in children

Donald J. Mabbott
Michael Noseworthy
Eric Bouffet
Suzanne Laughlin
Conrad Rockel

We examined the functional role of white matter growth in cognitive development. Specifically, we used hierarchical regression analyses to test the unique contributions of age versus white matter integrity in accounting for the development of information processing speed. Diffusion tensor imaging was acquired for 17 children and adolescents (age range 6–17 years), with apparent diffusion coefficient (ADC) and fractional anisotropy (FA) calculated for 10 anatomically defined fiber pathways and 12 regions of hemispheric white matter. Measures of speeded visual–spatial searching, rapid picture naming, reaction time in a sustained attention task, and intelligence were administered. Age-related increases were evident across tasks, as well as for white matter integrity in hemispheric white matter. ADC was related to few measures. FA within multiple hemispheric compartments predicted rapid picture naming and standard error of reaction time in sustained attention, though it did not contribute significantly to the models after controlling for age. Independent of intelligence, visual–spatial searching was related to FA in a number of hemispheric regions. A novel finding was that only right frontal–parietal regions contributed uniquely beyond the effect of age in accounting for performance: age did not contribute to visual–spatial searching when FA within these regions was first included in the models. Considering we found that both FA in right frontal–parietal regions and speed of visual–spatial searching increased with age, our findings are consistent with the growth of regional white matter organization as playing an important role in increased speed of visual searching with age.

Details DOI