Juan M. Calderón

Trends in Mobile Cyber-Physical Systems for health Just-in time interventions

Advances in pervasive computing, machine learning, and human activity recognition are changing preventive health care. Emerging paradigms, such as Mobile Cyber-Physical System (MCPS) and Just-in-time interventions (JITI), allow patients to take health monitoring, diagnosis, therapy and treatments beyond traditional medical settings. These paradigms empower patients by delivering health care at any place and at any time. MCPS provides the necessary engineering support to enable JITI systems to work in an autonomous way. In this work, we review the recent trends in the design of Mobile Cyber-Physical systems for Just-in-time interventions (MCP-JITI), and the different engineering concepts behind this paradigm. Finally, we discuss a set of necessary requirements or design issues to successfully deploy in real world scenarios. This discussion is driven by the description of the MCP-JITI architecture and the interconnections among its components.

Optimizing Energy Usage through Variable Joint Stiffness Control during Humanoid Robot Walking

The objective of this paper and our current research is to optimize energy usage in a humanoid robot during diverse tasks such as basic walking by dynamically controlling individual joint stiffness. In the current work we analyze individual and total usage of current, voltage and power in a NAO V4 humanoid robot joints during short walks around a circle at different speeds and under varying control of joint stiffness. We perform experimental studies to understand the main factors affecting power consumption and energy usage and look at ways to improve overall energy usage. We describe experiments and corresponding results. We discuss the state of advancement of our research.

Reduction of impact force in falling robots using variable stiffness

The work described in this paper is focused on the reduction of the impact force exerted by the ground on a falling humanoid robot. It proposes the use of variable stiffness to prevent the motors from damaging when falling is inevitable and the only possible strategy is the protection of the robot using its arms. A fuzzy system is used to estimate the low motor stiffness required to reduce the impact force. The stiffness value is obtained using information about the robot velocity at the moment of impact and the desired impact force. The proposed algorithm is implemented in a virtual Darwin OP humanoid robot. The performance of the proposed algorithm is evaluated through the estimation of the impact force.

Fuzzy Variable Stiffness in Landing Phase for Jumping Robot

Some important applications of humanoid robots in the nearest future are elder care, search and rescue of human victims in disaster zones and human machine interaction. Humanoid robots require a variety of motions and appropriate control strategies to accomplish those applications. This work focuses on vertical jump movements with soft landing. The principal objective is to perform soft contact allowing the displacement of the Center of Mass (CoM) in the landing phase. This is achieved by affecting the nominal value of the constant parameter P in the PID controller of the knee and ankle motors. During the vertical jump phases, computed torque control is applied. Additionally, in the landing phase, a fuzzy system is used to compute a suitable value for P, allowing the robot to reduce the impact through CoM displacement. The strategy is executed on a gait robot of three Degrees of Freedom (DoF). The effect of the impact reduction is estimated with the calculations of the CoM displacement and the impact force average during the landing phase.

Robot Swarms Theory Applicable to Seek and Rescue Operation.

An important application of cooperative robotics is search and rescue of victims in disaster zones. The cooperation between robots requires multiple factors that need to be taken into consideration such as communication between agents, distributed control, power autonomy, cooperation, navigation strategy, locomotion, among others. This work focuses on navigation strategy with obstacles avoidance and victims localization. The strategy used for navigation is based on swarm theory where each robot is an swarm agent. The calculation of attraction and repulsion forces used to keep the swarm compact is used to avoid obstacles and attract the swarm to the victim zones. Additionally, an agent separation behavior is added, so the swarm can leave behind the agents, who found victims so these can support the victims by transmitting their location to a rescue team. Several experiments were performed to test navigation, obstacle avoidance and victims search. The results show how the swarm theory meets the requirements of navigation and search operations of cooperative robots.

Identification of Multimodal Human-Robot Interaction Using Combined Kernels

In this paper we propose a methodology to build multiclass classifiers for the human-robot interaction problem. Our solution uses kernel-based classifiers and assumes that each data type is better represented by a different kernel. The kernels are then combined into one single kernel that uses all the dataset involved in the HRI process. The results on real data shows that our proposal is capable of obtaining lower generalization errors due to the use of specific kernels for each data type. Also, we show that our proposal is more robust when presented to noise in either or both data types.

Learning Soccer Drills for the Small Size League of RoboCup

This paper shows the results of applying machine learning techniques to the problem of predicting soccer plays in the Small Size League of RoboCup. We have modeled the task as a multi-class classification problem by learning the plays of the STOx’s team. For this, we have created a database of observations for this team’s plays and obtained key features that describe the game state during a match. We have shown experimentally, that these features allow two learning classifiers to obtain high prediction accuracies and that most miss-classified observations are found early on the plays.

Analyzing and Reducing Energy Usage in a Humanoid Robot During Standing Up and Sitting Down Tasks

The aim of this paper is to reduce the energy consumption of a humanoid by analyzing electrical power as input to the robot and mechanical power as output. The analysis considers motor dynamics during standing up and sitting down tasks. The motion tasks of the humanoid are described in terms of joint position, joint velocity, joint acceleration, joint torque, center of mass (CoM) and center of pressure (CoP). To reduce the complexity of the robot analysis, the humanoid is modeled as a planar robot with four links and three joints. The humanoid robot learns to reduce the overall motion torque by applying Q-Learning in a simulated model. The resulting motions are evaluated on a physical NAO humanoid robot during standing up and sitting down tasks and then contrasted to a pre-programmed task in the NAO. The stand up and sit down motions are analyzed for individual joint current usage, power demand, torque, angular velocity, acceleration, CoM and CoP locations. The overall result is improved energy efficiency between 25–30% when compared to the pre-programmed NAO stand up and sit down motion task.

Fast Path Planning Algorithm for the RoboCup Small Size League

Plenty of work based on the Rapidly-exploring Random Trees (RRT) algorithm for path planning in real time has been developed recently. This is the most used algorithm by the top research teams in the Small Size League of RoboCup. Nevertheless, we have concluded that other simpler alternatives show better results under these highly dynamic environments. In this work, we propose a new path planning algorithm that meets all the robotic soccer challenges requirements, which has already been implemented in the STOx’s team for the RoboCup competition in 2013. We have evaluated the algorithm’s performance using metrics such as the smoothness of the paths, the traveled distance and the processing time and compared it with the RRT algorithm’s. The results showed improved performance over RRT when combined measures are used.

Comparison between a fuzzy controller and classic controller applied to stabilize a humanoid robotic platform

In this paper, we perform a comparison between classical PI+D control strategies with a fuzzy modified PI+D control. The fuzzy PI+D controller is a discrete-time version of the conventional PI+D controller, which has constant coefficients of self-tuned control gains. The proposed control strategies were tested using a mathematical model based on a bipedal platform robot called DARwIn-OP. A mathematical model was developed to emulate robot behavior and dynamical performance. It is a linear model based on non linear conditions. The main improvement of the fuzzy controller is its adaptive control capability, mainly error acquisition under disturbance situations. Computer simulations are shown to demonstrate fuzzy modified controller improvements over the classic PI+D controller applied on mathematical robot model.