Aman Behal

Amirhossein Jabalameli, Aman Behal

In this paper, the parameter estimation problem for a multi-timescale adaptive threshold (MAT) neuronal model is investigated. By manipulating the system dynamics, which comprise of a non-resetting leaky integrator coupled with an adaptive threshold, the threshold voltage can be obtained as a realizable model that is linear in the unknown parameters. This linearly parametrized realizable model is then utilized inside a prediction error based framework to identify the threshold parameters with the purpose of predicting single neuron precise firing times. The iterative linear least squares estimation scheme is evaluated using both synthetic data obtained from an exact model as well as experimental data obtained from in vitro rat somatosensory cortical neurons. Results show the ability of this approach to fit the MAT model to different types of fluctuating reference data. The performance of the proposed approach is seen to be superior when comparing with existing identification approaches used by the neuronal community.

Michael A. Rupp, Aman Behal

Cyber human interaction is a broad term encompassing the range of interactions that humans can have with technology. While human interaction with fixed and mobile computers is well understood, the world is on the cusp of ubiquitous and sustained interactions between humans and robots. While robotic systems are intertwined with computing and computing technologies, the word robot here describes technologies that can physically affect and in turn be affected by their environments which includes humans. This chapter delves into issues of cyber human interaction from the perspective of humans interacting with a subset of robots known as assistive robots. Assistive robots are robots designed to assist individuals with mobility or capacity limitations in completing everyday activities, commonly called instrumental activities of daily living. These range from household chores, eating or drinking to any activity with which a user may need the daily assistance of a caregiver to complete. One common type of assistive robot is the wheelchair mounted robotic arm. This device is designed to attach to a user's wheelchair to allow him or her to complete their activities independently. In short, these devices have sensors that allow them to sense and process their environment with varying levels of autonomy to perform actions that benefit and improve the well-being of people with capability limitations or disabilities. While human robot interaction is a popular research topic, not much research has been dedicated with regard to individual with limitations. In this chapter, we provide an overview of assistive robotic devices, discuss common methods of user interaction, and the need for an adaptive compensation framework to support potential users in regaining their functional capabilities.

Masoud Baghbahari, Aman Behal

Tactile perception is an essential ability of intelligent robots in interaction with their surrounding environments. This perception as an intermediate level acts between sensation and action and has to be defined properly to generate suitable action in response to sensed data. In this paper, we propose a feedback approach to address robot grasping task using force-torque tactile sensing. While visual perception is an essential part for gross reaching, constant utilization of this sensing modality can negatively affect the grasping process with overwhelming computation. In such case, human being utilizes tactile sensing to interact with objects. Inspired by, the proposed approach is presented and evaluated on a real robot to demonstrate the effectiveness of the suggested framework. Moreover, we utilize a deep learning framework called Deep Calibration in order to eliminate the effect of bias in the collected data from the robot sensors.

Masoud Baghbahari, Aman Behal

Real time applications such as robotic require real time actions based on the immediate available data. Machine learning and artificial intelligence rely on high volume of training informative data set to propose a comprehensive and useful model for later real time action. Our goal in this paper is to provide a solution for robot grasping as a real time application without the time and memory consuming pertaining phase. Grasping as one of the most important ability of human being is defined as a suitable configuration which depends on the perceived information from the object. For human being, the best results obtain when one incorporates the vision data such as the extracted edges and shape from the object into grasping task. Nevertheless, in robotics, vision will not suite for every situation. Another possibility to grasping is using the object shape information from its vicinity. Based on these Haptic information, similar to human being, one can propose different approaches to grasping which are called grasping policies. In this work, we are trying to introduce a real time policy which aims at keeping contact with the object during movement and alignment on it. First we state problem by system dynamic equation incorporated by the object constraint surface into dynamic equation. In next step, the suggested policy to accomplish the task in real time based on the available sensor information will be presented. The effectiveness of proposed approach will be evaluated by demonstration results.

Amirhossein Jabalameli, Nabil Ettehadi, Aman Behal

In this paper, we investigate the problem of grasping novel objects in unstructured environments. To address this problem, consideration of the object geometry, reachability and force closure analysis are required. We propose a framework for grasping unknown objects by localizing contact regions on the contours formed by a set of depth edges in a single view 2D depth image. According to the edge geometric features obtained from analyzing the data of the depth map, the contact regions are determined. Finally,We validate the performance of the approach by applying it to the scenes with both single and multiple objects, using Baxter manipulator.

Rouhollah Rahmatizadeh, Pooya Abolghasemi, Aman Behal et al.

Robots assisting the disabled or elderly must perform complex manipulation tasks and must adapt to the home environment and preferences of their user. Learning from demonstration is a promising choice, that would allow the non-technical user to teach the robot different tasks. However, collecting demonstrations in the home environment of a disabled user is time consuming, disruptive to the comfort of the user, and presents safety challenges. It would be desirable to perform the demonstrations in a virtual environment. In this paper we describe a solution to the challenging problem of behavior transfer from virtual demonstration to a physical robot. The virtual demonstrations are used to train a deep neural network based controller, which is using a Long Short Term Memory (LSTM) recurrent neural network to generate trajectories. The training process uses a Mixture Density Network (MDN) to calculate an error signal suitable for the multimodal nature of demonstrations. The controller learned in the virtual environment is transferred to a physical robot (a Rethink Robotics Baxter). An off-the-shelf vision component is used to substitute for geometric knowledge available in the simulation and an inverse kinematics module is used to allow the Baxter to enact the trajectory. Our experimental studies validate the three contributions of the paper: (1) the controller learned from virtual demonstrations can be used to successfully perform the manipulation tasks on a physical robot, (2) the LSTM+MDN architectural choice outperforms other choices, such as the use of feedforward networks and mean-squared error based training signals and (3) allowing imperfect demonstrations in the training set also allows the controller to learn how to correct its manipulation mistakes.