Adam Norton

Adam Norton


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
IGIrene Garcia-Camacho
Irene Garcia-Camacho
JBJulia Borras
Julia Borras
BCBerk Calli
Berk Calli
ANAdam Norton
Adam Norton
GAGuillem Alenyà
Guillem Alenyà
Benchmarking of robotic manipulations is one of the open issues in robotic research. An important factor that has enabled progress in this area in the last decade is the existence of common object sets that have been shared among different research groups. However, the existing object sets are very limited when it comes to cloth-like objects that have unique particularities and challenges. This letter is a first step towards the design of a cloth object set to be distributed among research groups from the robotics cloth manipulation community. We present a set of household cloth objects and related tasks that serve to expose the challenges related to gathering such an object set and propose a roadmap to the design of common benchmarks in cloth manipulation tasks, with the intention to set the grounds for a future debate in the community that will be necessary to foster benchmarking for the manipulation of cloth-like objects. Some RGB-D and object scans are collected as examples for the relevant configurations and shared in http://www.iri.upc.edu/groups/perception/ClothObjectSet/ .

13 July 2022 in ACM Transactions on Human-Robot Interaction
Verified
Journal Article
Open access
ANAdam Norton
Adam Norton
HAHenny Admoni
Henny Admoni
JCJacob Crandall
Jacob Crandall
TFTesca Fitzgerald
Tesca Fitzgerald
AGAlvika Gautam
Alvika Gautam
HYHolly Yanco
Holly Yanco
As development of robots with the ability to self-assess their proficiency for accomplishing tasks continues to grow, metrics are needed to evaluate the characteristics and performance of these robot systems and their interactions with humans. This proficiency-based human-robot interaction (HRI) use case can occur before, during, or after the performance of a task. This article presents a set of metrics for this use case, driven by a four-stage cyclical interaction flow: (1) robot self-assessment of proficiency (RSA), (2) robot communication of proficiency to the human (RCP), (3) human understanding of proficiency (HUP), and (4) robot perception of the human’s intentions, values, and assessments (RPH). This effort leverages work from related fields including explainability, transparency, and introspection, by repurposing metrics under the context of proficiency self-assessment. Considerations for temporal level (a priori, in situ, and post hoc) on the metrics are reviewed, as are the connections between metrics within or across stages in the proficiency-based interaction flow. This article provides a common framework and language for metrics to enhance the development and measurement of HRI in the field of proficiency self-assessment.

4 October 2018 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
JMJeffrey Mahler
Jeffrey Mahler
RPRob Platt
Rob Platt
ARAlberto Rodriguez
Alberto Rodriguez
MCMatei Ciocarlie
Matei Ciocarlie
ADAaron Dollar
Aaron Dollar
KGKen Goldberg
Ken Goldberg
Automated grasping has a long history of research that is increasing due to interest from industry. One grand challenge for robotics is Universal Picking: the ability to robustly grasp a broad variety of objects in diverse environments for applications from warehouses to assembly lines to homes. Although many researchers now openly share code and data, it is challenging to compare and/or reproduce experimental results to identify which aspects of which approaches work best due to variations in assumptions and experimental protocols, e.g., sensors, lighting, robot arms, grippers, and objects.

6 January 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JFJoe Falco
Joe Falco
DHDaniel Hemphill
Daniel Hemphill
KKKenny Kimble
Kenny Kimble
EMElena Messina
Elena Messina
ANAdam Norton
Adam Norton
HYHolly Yanco
Holly Yanco
This letter describes a set of metrics and supporting benchmarking protocols for determining the performance characteristics of robot end-effectors. In the short-term, these tools are proving useful as a common ground for assessing and comparing end-effectors. The long-term goal is a standard framework for providing technical specifications for robotic end-effectors to help pair technologies to application spaces. This letter presents a subset of the metrics - grasp strength, grasp cycle time, finger strength, and finger repeatability - with accompanying measurement techniques and supporting test artifacts. The application of these metrics and protocols is demonstrated using example implementations to characterize a variety of robot end-effectors, with example data sets and test designs provided for downloading.

27 September 2021
Verified
Conference Paper
Open access
WLWenzhao Lian
Wenzhao Lian
TKTim Kelch
Tim Kelch
DHDirk Holz
Dirk Holz
ANAdam Norton
Adam Norton
SSStefan Schaal
Stefan Schaal
In recent years, many learning based approaches have been studied to realize robotic manipulation and assembly tasks, often including vision and force/tactile feedback. How-ever, it is unclear what the baseline state-of-the-art performance is and what the bottleneck problems are. In this work, we evaluate off-the-shelf (OTS) industrial solutions on a recently introduced benchmark, the National Institute of Standards and Technology (NIST) Assembly Task Board. A set of assembly tasks is introduced and baseline methods are provided to understand their intrinsic difficulty. Multiple sensor-based robotic solutions are then evaluated, including hybrid force/motion control and 2D/3D pattern matching. An end-to-end integrated solution that accomplishes the tasks is also provided.The results and findings throughout the study reveal a few noticeable factors that impede the adoptions of the OTS solutions: dependency on expertise, limited applicability, lack of interoperability, no scene awareness or error recovery mechanisms, and high cost. This paper also provides a first attempt of an objective benchmark performance on the NIST Assembly Task Boards as a reference comparison for future works on this problem.

1 February 2019 in Smart and Sustainable Manufacturing Systems
Verified
Journal Article
Closed access
ANAdam Norton
Adam Norton
PGPeter Gavriel
Peter Gavriel
HYHolly Yanco
Holly Yanco
Automatic guided vehicles (AGVs) and autonomous mobile robots (AMRs) are now ubiquitous in industrial manufacturing environments. These systems all must possess a similar set of core capabilities, including navigation, obstacle avoidance, and localization. However, there are few standard methods to evaluate the capabilities and limitations of these systems in a way that is comparable. In this article, a standard test method is presented that can be used to evaluate these capabilities and can be easily scaled and augmented according to the characteristics of the system under test. The test method can be configured in a variety of ways to exercise different capabilities, all using a common test apparatus to ease test setup and increase versatility. For each test configuration, conditions are specified with respect to the a priori knowledge provided to the system (e.g., boundary or obstacle locations) and the obstacles in the environment. Robustness of system capabilities is evaluated by purposefully introducing misalignment between the characteristics of the physical and virtual environments (e.g., providing representations of obstacles in the system’s map when they are not physically present). Example test performance data from an AMR are provided. The goal of this work is to provide a common method to characterize the performance of mobile systems in industrial environments that is easily comparable and communicated for both commercial and developmental purposes. This work is driven by existing standards and those in development by the ASTM F45 Committee on Driverless Automatic Guided Industrial Vehicles and will influence the development of new standards within the committee.