Learning to slide a magnetic card through a card reader

Sukhoy, Vladimir; Georgiev, Veselin; Wegter, Todd; Sweidan, Ramy; Stoytchev, Alexander

doi:10.1109/icra.2012.6225358

Cited by 13 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sukhoy et al [16] learned the trajectory for sliding a card through a card reader with proprioceptive feedback. Sturm et al [17] learned a kinematic model for successfully opening various doors using a F/T sensor.…”

Section: Skill Acquisition and Monitoringmentioning

confidence: 99%

Learning haptic affordances from demonstration and human-guided exploration

Chu

Akgün

Thomaz

2016

2016 IEEE Haptics Symposium (HAPTICS)

View full text Add to dashboard Cite

In this paper, we present a system for learning haptic affordance models of complex manipulation skills. The goal of a haptic affordance model is to better complete tasks by characterizing what a particular object-action pair feels like. We use learning from demonstration to provide the robot with an example of a successful interaction with a given object. We then use environmental scaffolding to collect grounded examples (successes and unsuccessful "near misses") of the haptic data for the object-action pair, using a force/torque (F/T) sensor mounted at the wrist. From this we build one success Hidden Markov Model (HMM) and one "near-miss" HMM for each object-action pair. We evaluate this approach with five different actions over seven different objects to learn two specific affordances (open-able and scoop-able). We show that by building a library of object-action pairs for each affordance, we can successfully monitor a trajectory of haptic data to determine if the robot finds an affordance. This is supported through cross-validation on the object-action pairs, with four of the seven object-action pairs achieving a perfect F 1 score, and with leave-one-object-out testing, where the learned objectactions models correctly identify the specific affordance with an average accuracy of 67% for scoop-able and 53% for open-able.

show abstract

Section: Skill Acquisition and Monitoringmentioning

confidence: 99%

Learning haptic affordances from demonstration and human-guided exploration

Chu

Akgün

Thomaz

2016

2016 IEEE Haptics Symposium (HAPTICS)

View full text Add to dashboard Cite

show abstract

“…For example, assessing joint torque values can be an indicator of whether the motion of the end effector is constrained [8]. Therefore the second aspect that we address is detecting axes in task space where force control applies and encoding these force profiles.…”

Section: Related Workmentioning

confidence: 99%

“…The second segmentation involves searching for zero velocity crossings (ZVC) [17] or other changes in a variable compared to a known state [8]. This approach is sensitive to the variables encoded while one needs to find a way that would ensure optimal segmentation across all task dimensions.…”

Section: Related Workmentioning

confidence: 99%

Task Parameterization Using Continuous Constraints Extracted From Human Demonstrations

et al. 2015

View full text Add to dashboard Cite

Abstract-In this work we propose an approach for learning task specifications automatically, by observing human demonstrations. Using this allows a robot to combine representations of individual actions to achieve a high-level goal. We hypothesize that task specifications consist of variables that present a pattern of change that is invariant across demonstrations. We identify these specifications at different stages of task completion. Changes in task constraints allow us to identify transitions in the task description and to segment them into sub-tasks. We extract the following task-space constraints: (1) the reference frame in which to express the task variables, (2) the variable of interest at each time step, position or force at the end effector; and (3) a factor that can modulate the contribution of force and position in a hybrid impedance controller. The approach was validated on a 7 DOF Kuka arm, performing 2 different tasks: grating vegetables and extracting a battery from a charging stand.

show abstract

“…In recent years, magnetic cards are used for cash cards, patient registration cards, membership cards, security cards and the like. A long and narrow magnetic stripe embedded in a surface of a magnetic card has digital data such as a number for identifying a user, magnetically recorded therein [1-3]. Depending on the different materials, magnetic cards can be divided into three kinds: PET cards, polyvinyl chloride cards and paper card.…”

Section: Introductionmentioning

confidence: 99%

The Design of High Performance, Low Power Triple-Track Magnetic Sensor Chip

Lin

et al. 2013

Sensors

View full text Add to dashboard Cite

This paper presents a design of a high performance and low power consumption triple-track magnetic sensor chip which was fabricated in TSMC 0.35 μm CMOS process. This chip is able to simultaneously sense, decode and read out the information stored in triple-track magnetic cards. A reference voltage generating circuit, a low-cost filter circuit, a power-on reset circuit, an RC oscillator, and a pre-decoding circuit are utilized as the basic modules. The triple-track magnetic sensor chip has four states, i.e., reset, sleep, swiping card and data read-out. In sleep state, the internal RC oscillator is closed, which means that the digital part does not operate to optimize energy consumption. In order to improve decoding accuracy and expand the sensing range of the signal, two kinds of circuit are put forward, naming offset correction circuit, and tracking circuit. With these two circuits, the sensing function of this chip can be more efficiently and accurately. We simulated these circuit modules with TSMC technology library. The results showed that these modules worked well within wide range input signal. Based on these results, the layout and tape-out were carried out. The measurement results showed that the chip do function well within a wide swipe speed range, which achieved the design target.

show abstract

Learning to slide a magnetic card through a card reader

Cited by 13 publications

References 13 publications

Learning haptic affordances from demonstration and human-guided exploration

Learning haptic affordances from demonstration and human-guided exploration

Task Parameterization Using Continuous Constraints Extracted From Human Demonstrations

The Design of High Performance, Low Power Triple-Track Magnetic Sensor Chip

Contact Info

Product

Resources

About