A5090798236- Traffic control and management
- Smart Grid Energy Management
- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Robotic Locomotion and Control
- Auction Theory and Applications
- Robotic Path Planning Algorithms
- Advanced Data Compression Techniques
- Image and Signal Denoising Methods
- Reinforcement Learning in Robotics
- Transportation and Mobility Innovations
- Optimization and Search Problems
- Data Management and Algorithms
- Simulation Techniques and Applications
- Electric Power System Optimization
- Autonomous Vehicle Technology and Safety
- Image Retrieval and Classification Techniques
- Distributed Control Multi-Agent Systems
- Algorithms and Data Compression
- Biomedical and Engineering Education
- Building Energy and Comfort Optimization
- Refrigeration and Air Conditioning Technologies
- Vehicular Ad Hoc Networks (VANETs)
- Model-Driven Software Engineering Techniques
- Energy Efficiency and Management
Herzliya Medical Center
2025
The University of Texas at Austin
2011-2021
Tel Aviv University
2004-2006
This paper introduces a novel control framework for Lagrangian variable speed limits in hybrid traffic flow environments utilizing automated vehicles (AVs). The was validated using fleet of 100 connected as part the largest coordinated open-road test designed to smooth flow. includes two main components: high-level controller deployed on server side, named Speed Planner, and low-level controllers called vehicle side. Planner designs updates target speeds based real-time Traffic State...
This paper presents the design and learning architecture for an omnidirectional walk used by a humanoid robot soccer agent acting in RoboCup 3D simulation environment. The walk, which was originally designed tested on actual Nao before being employed 2011 competition, crucial component UT Austin Villa team winning competition 2011. To best of our knowledge, this is first time that behavior has been conceived constructed real end purpose simulation. based double linear inverted pendulum...
Sustainable energy systems of the future could no longer rely on current paradigm that supply follows demand. Since many renewable resources do not produce power demand, there is a need for new market structures motivate sustainable behaviors by participants. The Power Trading Agent Competition(Power TAC) annual competition focuses design and operation retail markets, specifically in smart grid environments with production, metering, autonomous agents acting behalf customers retailers. It...
Heating, Ventilation and Air Conditioning (HVAC) systems are one of the biggest energy consumers around world. With efforts moving to sustainable consumption, heat-pump based HVAC have gained popularity due their high efficiency fact that they powered by electricity rather than gas or oil. One drawback is sharply decreases when outdoor temperature below freezing. Therefore, backed up an auxiliary heating system effective in cold whether, but consumes twice as much energy. A popular way...
In several realistic domains an agent's behavior is composed of multiple interdependent skills. For example, consider a humanoid robot that must play soccer, as the focus this paper. order to succeed, it clear needs walk quickly, turn sharply, and kick ball far. However, these individual skills are ineffective if falls down when switching from walking turning, or cannot position itself behind for kick.This paper presents learning architecture soccer agent has been fully deployed tested...
The problem of multiagent patrol has gained considerable attention during the past decade, with immediate applicability being one its main sources interest. In this paper we concentrate on frequency-based patrol, in which agents' goal is to optimize a frequency criterion, namely, minimizing time between visits set interest points. We consider environments complex environmental conditions that affect cost traveling from point another. For example, marine environments, travel ships depends...
Sustainable energy systems of the future will no longer be able to rely on current paradigm that supply follows demand. Many renewable resources do not produce power demand, and therefore there is a need for new market structures motivate sustainable behaviors by participants. The Power Trading Agent Competition (Power TAC) annual competition focuses design operation retail markets, specifically in smart grid environments with production, metering, autonomous agents acting behalf customers...
This paper presents the architecture and key components of a simulated humanoid robot soccer team, UT Austin Villa, which was designed to compete in RoboCup 3D simulation competition. These include (1) an omnidirectional walk engine associated parameter optimization framework, (2) inverse kinematics based kicking architecture, (3) dynamic role assignment positioning system. Villa won 2011 competition convincing fashion by winning all 24 games it played. During course team scored 136 goals...
This paper studies the impact of Time-Of-Use (TOU) tariffs in a competitive electricity market place. Specifically, it focuses on question how should an autonomous broker agent optimize TOU retail market, and what is such economy. We formalize problem tariff optimization propose algorithm for approximating its solution. extensively experiment with our large-scale, detailed markets simulation Power Trading Agent Competition (Power TAC) and: 1) find that results 15% peak-demand reduction, 2)...
With the efforts of moving to sustainable and reliable energy supply, electricity markets are undergoing far-reaching changes. Due high-cost failure in real-world, it is important test new market structures simulation. This focus Power Trading Agent Competition (Power TAC), which proposes autonomous broker agents as a means for stabilizing grid. paper focuses on question: how should an agent act competitive maximize its profit. We formalize trading problem continuous, high-dimensional Markov...
The smart grid is envisioned to be a main enabler of sustainable, clean, efficient, reliable, and secure energy supply (U.S. Department Energy, 2003). One the milestones in vision will programs for customer participation electricity markets through demand-side management distributed generation; incentivize customers adapt their demand conditions, which help utilize intermittent resources such as from solar wind, reduce peak-demand.
The proliferation of Connected Automated Vehicles represents an unprecedented opportunity for improving driving efficiency and alleviating traffic congestion. However, existing research fails to address realistic multi-lane highway scenarios without assuming connectivity, perception, control capabilities that are typically unavailable in current vehicles. This paper proposes a novel AI system is the first improve compared with human-like realistic, simulated scenarios, while relying on...
In the problem of multiagent patrol, a team agents is required to repeatedly visit target area in order monitor possible changes state. The growing popularity this comes mainly from its immediate applicability wide variety domains. paper we concentrate on frequency-based which agents' goal optimize frequency criterion, namely, minimizing time between visits set interest points. situations with varying environmental conditions, influence conditions cost travel may be immense. For example,...