Çetin Meriçli

Carnegie Mellon University, Robotics Institute, Senior Robotics Engineer

Followers

185

Following

Co-authors

Public Views

Supervisors: Levent Akin and Manuela Veloso

less

InterestsView All (18)

Uploads

Papers by Çetin Meriçli

Cerberus 2003 team report

by Çetin Meriçli, Olcay Taner Yildiz, and Ömer Sever

A robust statistical collision detection framework for quadruped robots

by Tekin Meriçli and Çetin Meriçli

RoboCup 2008: Robot Soccer World Cup XII, Jan 1, 2009

In order to achieve its tasks in an effective manner, an autonomous mobile robot must be able to ... more In order to achieve its tasks in an effective manner, an autonomous mobile robot must be able to detect and quickly recover from collisions. This paper proposes a new solution to the problem of detecting collisions during omnidirectional motion of a quadruped robot equipped with an internal accelerometer. We consider this as an instance of general signal processing and statistical anomaly detection problems. We find that temporal accelerometer readings examined in the frequency domain are good indicators of regularities (normal motion) and novel situations (collisions). In the course of time, the robot builds a probabilistic model that captures its proprioceptive properties while walking without obstruction and uses that model to determine whether there is an abnormality in the case of an unfamiliar pattern. The approach does not depend on walk characteristics and the walking algorithm used, and is insensitive to the surface texture that the robot walks on as long as the surface is flat. The experiments demonstrate quite fast and successful detection of collisions independent of the point of contact with an acceptably low false positive rate.

Download

Derivation of gaze direction from head pose estimates

by Tekin Meriçli, Albert Ali Salah, and Çetin Meriçli

Automatic estimation of gaze direction information is important for certain applications of human... more Automatic estimation of gaze direction information is important for certain applications of human-robot and human-computer interaction. Depending on the properties of the specific application, it may be required to derive this information in real time from low resolution visual inputs, with as much precision as possible. In this paper we present an algorithm for transforming head pose estimates to gaze direction estimates. The main contribution of this study lies in the fact that it makes a clear distinction between head pose and gaze direction. Unlike some of the previous works in this field, we do not correct the head pose to correspond to a possible attention fixation point in accordance with the experiment scenario. Instead we propose using a concrete and environment-independent method for this purpose. To transform the head pose estimates into gaze direction, a Gaussian process regression model is proposed and the reasons validating this choice are discussed in detail.

Cerberus’ 08 Standard Platform League Team Qualification Document

by Tekin Meriçli, Levent Akin, and Çetin Meriçli

“Cerberus” team made its debut in the 4-Legged league in RoboCup 2001 competition. This was the f... more “Cerberus” team made its debut in the 4-Legged league in RoboCup 2001 competition. This was the first international team participating in the league as a result of the joint research effort of Bogaziçi University (BU), Istanbul, Turkey and Technical University Sofia, Plovdiv branch (TUSP), Plovdiv, Bulgaria [1]. The team competed in Robocup since then, except Robocup 2004. Since 2004, Bogaziçi University is maintaining the team.

Download

Joint Attention by Gaze Interpolation and Saliency

by Tekin Meriçli, Çetin Meriçli, and Theo Gevers

Joint attention, which is the ability of coordination of a common point of reference with the com... more Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The precise analysis of the experimenter&amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s eye region requires stability and high-resolution image acquisition, which is not always available. We investigate regression-based interpolation of the gaze direction from the head pose of the experimenter, which is easier to track. Gaussian process regression and neural networks are contrasted to interpolate the gaze direction. Then, we combine gaze interpolation with image-based saliency to improve the target point estimates and test three different saliency schemes. We demonstrate the proposed method on a human-robot interaction scenario. Cross-subject evaluations, as well as experiments under adverse conditions (such as dimmed or artificial illumination or motion blur), show that our method generalizes well and achieves rapid gaze estimation for establishing joint attention.

Robot detection with a cascade of boosted classifiers based on haar-like features

by Tekin Meriçli, Çetin Meriçli, and Levent Akin

… 2010: Robot Soccer World Cup XIV, Jan 1, 2011

Accurate world modeling is important for efficient multi-robot planning in robot soccer. Visual d... more Accurate world modeling is important for efficient multi-robot planning in robot soccer. Visual detection of the robots on the field in addition to all other objects of interest is crucial to achieve this goal. The problem of robot detection gets even harder when robots with only on board sensing capabilities, limited field of view, and restricted processing power are used. This work extends the real-time object detection framework proposed by Viola and Jones, and utilizes the unique chest and head patterns of Nao humanoid robots to detect them in ...

Robot Detection with a Cascade of Boosted Classifiers Based on Haar-Like Features

Joint visual attention modeling for naturally interacting robotic agents

This paper elaborates on mechanisms for establishing visual joint attention for the design of rob... more This paper elaborates on mechanisms for establishing visual joint attention for the design of robotic agents that learn through natural interfaces, following a developmental trajectory not unlike infants. We describe first the evolution of cognitive skills in infants and then the adaptation of cognitive development patterns in robotic design. A comprehensive outlook for cognitively inspired robotic design schemes pertaining to joint attention is presented for the last decade, with particular emphasis on practical implementation issues. A novel cognitively inspired joint attention fixation mechanism is defined for robotic agents.

Download

A reward function generation method using genetic algorithms: a robot soccer case study

Immediate rewards play a key role in a reinforcement learning (RL) scenario as they help the syst... more Immediate rewards play a key role in a reinforcement learning (RL) scenario as they help the system deal with the credit assignment problem. Therefore, reward function definition has a drastic effect on both how fast the system learns and to what policy it converges. It becomes even more important in case of multi-agent learning, where the state space usually gets even bigger. We propose a Genetic Algorithms (GA) based reward function shaping method for multi-robot learning problems and evaluate its performance in a robot soccer case study. A set of metrics calculated from the positions of the players and the ball on the field are used as the primitive building blocks of an immediate reward function, which is defined as a weighted combination of these metrics obtained using GA, yielding a significantly better soccer playing performance.

Download

Market-Driven Multi-Agent Collaboration in Robot Soccer Domain

Download

Better, faster, and cheaper: what is better software

Background: Defects are related to failures and they do not have much power for indicating a high... more Background: Defects are related to failures and they do not have much power for indicating a higher quality or a better system above the baseline that the end-users expect. Nevertheless, defect counts are commonly used as measures to capture the quality of a system. Further, the statistical association between internal design metrics and quality in terms of defects has been shown in previous work.

Download

A finite horizon DEC-POMDP approach to multi-robot task learning

Decision making under uncertainty is one of the key problems of robotics and this problem is even... more Decision making under uncertainty is one of the key problems of robotics and this problem is even harder in the multi-agent domain. Decentralized Partially Observable Markov Decision Process (DEC-POMDP) is an approach to model multi-agent decision making problems under uncertainty. There is no efficient exact algorithm to solve these problems since the worst case complexity of the general case has been shown to be NEXP-complete. This paper demonstrates the application of our proposed approximate solution algorithm, which uses evolution strategies, to various DEC-POMDP problems. We show that high level policies can be learned using simplified simulated environments which can readily be transferred to real robots despite having different observation and transition models in the training and the application domains.

Download

Improving Biped Walk Stability Using Real-Time Corrective Human Feedback

Robust walking is one of the key requirements for soccer playing humanoid robots. Developing such... more Robust walking is one of the key requirements for soccer playing humanoid robots. Developing such a biped walk algorithm is non-trivial due to the complex dynamics of the walk process. In this paper, we first present a method for learning a corrective closed-loop policy to improve the walk stability for the Aldebaran Nao robot using real-time human feedback combined with an open-loop walk cycle. The open-loop walk cycle is obtained from the recorded joint commands while the robot is walking using an existing walk algorithm as a black-box unit. We capture the corrective feedback signals delivered by a human using a wireless feedback mechanism in the form of corrections to the particular joints and we present experimental results showing that a policy learned from a walk algorithm can be used to improve the stability of another walk algorithm. We then follow up with improving the open-loop walk cycle using advice operators before performing real-time human demonstration. During the demonstration, we then capture the sensory readings and the corrections in the form of displacements of the foot positions while the robot is executing improved open-loop walk cycle. We then translate the feet displacement values into individual correction signals for the leg joints using a simplified inverse kinematics calculation. We use a locally weighted linear regression method to learn a mapping from the recorded sensor values to the correction values. Finally, we use a simple anomaly detection method by modeling the changes in the sensory readings throughout the walk cycle during a stable walk as normal distributions and executing the correction policy only if a sensory reading goes beyond the modeled values. Experimental results demonstrate an improvement in the walk stability.

Download

CERBERUS 2003 TEAM REPORT

Cerberus is a joint effort of Boğaziçi University (Turkey) and Technical University of Sofia, Plo... more Cerberus is a joint effort of Boğaziçi University (Turkey) and Technical University of Sofia, Plovdiv branch(Bulgaria). We have divided the robot software design into six major tasks, and worked on those tasks in parallel. Many modules were developed using several approaches and later integrated into the final system. In addition to using better algorithms, improvements in the code were also made. iv

Download

CMurfs: Carnegie Mellon United Robots for Soccer

Download

Efficient task execution and refinement through multi-resolution corrective demonstration

Abstract Computationally efficient task execution is very important for autonomous mobile robots ... more Abstract Computationally efficient task execution is very important for autonomous mobile robots endowed with limited on-board computational capabilities. Most robot control approaches assume fixed state and action representations, and use a single algorithm to map states to actions. However, not all instances of a given task require equally complex algorithms and equally detailed representations. The main motivation for this work is a desire to reduce the computational footprint of performing a task by allowing the robot to ...

Market-driven multi-agent collaboration in robot soccer domain

In recent robotic studies, in many key areas decoupled multi-agent systems have become more popul... more In recent robotic studies, in many key areas decoupled multi-agent systems have become more popular than complex single agent systems, where the former is more robust, fast and cheap to implement. The most important reason behind this preference is to eliminate the possibility of single point of failure, which is a vital concern for single complex agents.

Complementary humanoid behavior shaping using corrective demonstration

Abstract A humanoid robot can perform a task through a policy mapping from its sensed state to th... more Abstract A humanoid robot can perform a task through a policy mapping from its sensed state to the appropriate task actions. We assume that a hand-coded controller can capture such a mapping only for the basic cases of the given task. As the complexity of the situation increases, the harder it becomes to refine the controller, and such refinements are often tedious and error prone.

Download

A finite horizon DEC-POMDP approach to multi-robot task learning

Abstract Decision making under uncertainty is one of the key problems of robotics and this proble... more Abstract Decision making under uncertainty is one of the key problems of robotics and this problem is even harder in the multi-agent domain. Decentralized Partially Observable Markov Decision Process (DEC-POMDP) is an approach to model multi-agent decision making problems under uncertainty. There is no efficient exact algorithm to solve these problems since the worst case complexity of the general case has been shown to be NEXP-complete.

Download

Multi-humanoid world modeling in standard platform robot soccer

Abstract In the RoboCup Standard Platform League (SPL), the robot platform is the same humanoid N... more Abstract In the RoboCup Standard Platform League (SPL), the robot platform is the same humanoid NAO robot for all the competing teams. The NAO humanoids are fully autonomous with two onboard directional cameras, computation, multi-joint body, and wireless communication among them. One of the main opportunities of having a team of robots is to have robots share information and coordinate.

Download

Çetin Meriçli

Uploads

Papers by Çetin Meriçli

Log In