Overview of Robocup-2000- Overview of Robocup-2000- Champion Teams- FC Portugal Team Description: RoboCup 2000 Simulation League Champion- The Cornell Robocup Team- CS Freiburg: Doing the Right Thing in a Group- The UNSW RoboCup 2000 Sony Legged League Team- Challenge Award Finalists- Adaptive Path Planner for Highly Dynamic Environments- Communication and Coordination among heterogeneous Mid-Size Players: ART99- A Localization Method for a Soccer Robot Using a Vision-Based Omni-Directional Sensor- Behavior Classification with Self-Organizing Maps- Full Papers- Flexible Synchronisation Within RoboCup Environment: a Comparative Analysis- Extended Q-Learning: Reinforcement Learning Using Self-Organized State Space- And the Fans are Going Wild! SIG Plus MIKE- Fast and Accurate Robot Vision for Vision Based Motion- Design of Robocup-Rescue Viewers - Towards a Real World Emergency System -- From Multiple Images to a Consistent View- Omni-directional vision with a multi-part mirror- Observation strategy for decision making based on information criterion- Towards a Logical Approach for Soccer Agents Engineering- Bridging Gap between the Simulation and Robotics with a Global Vision System- Real-Time Estimating Spatial Configuration between Multiple Robots by Triangle and Enumeration Constraints- Framework of Distributed Simulation System for Multi-Agent Environment- Robust Real Time Color Tracking- Reinforcement Learning for 3 vs 2 Keepaway- Fault-tolerant self localization by case-based reasoning- PINO The Humanoid : A Basic Architecture- Poster Description- Team/goal-keeper coordination in the RoboCup mid-size league- RescueModel: A Multi-Agent Simulation of Bushfire Disaster Management- Vision-based Localization in RoboCup Environments- Collaborative Emergent Actions between Real Soccer Robots- The Statistics Proxy Server- Using Simulated RoboCup in Undergraduate Education- Path Planning of a Mobile Robot as a Discrete Optimization Problem and Adjustment of Weight Parameters in the Objective Function by Reinforcement Learning- Simulator Complex for Robocup Rescue Simulation Project - As Test-Bed for Multi-Agent Organizational Behavior in Emergency Case of Large-Scale Disaster- A Quadratic Programming Formulation of a Moving Ball Interception and Shooting Behaviour, and its Application to Neural Network Control- Keeping the Ball from CMUnited-99- Potential Tasks and Research Issues for Mobile Robots in RoboCup Rescue- Potential Field Approach to Short Term Action Planning in RoboCup F180 League- Robocup-Rescue Simulation: in case of Fire Fighting Planning- On Emergence of Scalable Tactical and Strategic Behaviour- Karlsruhe Brainstormers - A Reinforcement Learning approach to robotic soccer- Preliminary Studies of Dynamics of Physical Agents Ecosystems- RoboCup-Rescue Disaster Simulator Architecture- Improvement Continuous Valued Q-learning and its Application to Vision Guided Behavior Acquisition- Recognizing Formations in Opponent Teams- Simulation League- SBC++ Simulator Team- A Team- AT Humboldt 2000 (Team Description)- AIRG Sibiu- The NOAI Team Description- Improved Agents of the magmafreiburg2000 Team- Virtual Werder- Kakitsubata Team Description- PaSo-Team 2000- Sharif-Arvand Simulation Team- SharifII Soccer Simulation Team- Essex Wizards 2000 Team Description- RoboCup-2000 Simulation League: Team KU-Yam2000- Harmony Team- TakAI- PSI Team- PSI Team- Gnez: Adapting Knowledge to the Environment with GA- Gnez: Adapting knowledge to the environment with GA- Zeng00 : the Realization of Mixed Strategy in Simulation Soccer Game- Zeng00: The Realization of Mixed Strategy in simulation soccer game- RoboLog Koblenz 2000- RoboLog Koblenz 2000- Open Zeng: an Open Style Distributed Semi-Cooperative Team Development Project from Japan- Open Zeng: an Open Style Distributed Semi-Cooperative Team Development Project from Japan- Gemini in RoboCup-2000- Gemini in RoboCup-2000- Team Description for Lucky lubeck - Evidence-Based World State Estimation- Team Description for Lucky Lubeck - Evidence-Based World State Estimation- Karlsruhe Brainstormers 2000 Team Description- Karlsruhe Brainstormers 2000 Team Description- ATT-CMUnited-2000: Third Place Finisher in the Robocup-2000 Simulator League- ATT-CMUnited-2000: Third Place Finisher in the Robocup-2000 Simulator League- Headless Chickens IV- Headless Chickens IV- Mainz Rolling Brains 2000- Mainz Rolling Brains 2000- Team Description of Spatial-Timer- Team Description of Spatial-Timer- Polytech100- Polytech100- Team YowAI-2000 Description- Team YowAI-2000 Description- 11monkeysII- 11monkeysII- All Botz- All Botz- 4 Stooges- 4 Stooges- CIIPS Glory Small Soccer Robots with Local Image Processing- CIIPS Glory Small Soccer Robots with Local Image Processing- ViperRoos 2000- ViperRoos 2000- RoboCup 2000 (F180) Team Description : UPMC-CFA Team (France)- RoboCup 2000 (F180) Team Description : UPMC-CFA Team (France)- MuCows- MuCows- Role-Based Strategy in Tpots RoboCup Team- Role-Based Strategy in TPOTs RoboCup Team- LuckyStar II - Team Description Paper- LuckyStar II - Team Description Paper- FU-Fighters 2000- FU-Fighters 2000- RoGi Team Description- RoGi Team Description- UQ RoboRoos: Kicking on to 2000- UQ RoboRoos: Kicking on to 2000- ART'00 - Azzurra Robot Team for the Year 2000- ART'00 - Azzurra Robot Team for the Year 2000- RMIT United- RMIT United- Agilo RoboCuppers: RoboCup Team Description- Agilo RoboCuppers: RoboCup Team Description- WinKIT- WinKIT- CMU Hammerheads Team Description- CMU Hammerheads Team Description- GMD-Robots- GMD-Robots- A Goal Keeper for Middle Size Robocup- A Goal Keeper for Middle Size Robocup- The Dutch Team- The Dutch Team- The RoboCup-NAIST- The RoboCup-NAIST- KIRC: Kyutech Intelligent Robot Club- KIRC: Kyutech Intelligent Robot Club- CoPS-Team Description- CoPS-Team Description- Golem Team in Middle-Sized Robots League- Golem Team in Middle-Sized Robots League- Osaka University "Trackies 2000"- Osaka University "Trackies 2000"- Essex Rovers Team Description- Essex Rovers Team Description- French LRP Team's Description- French LRP Team's Description- Team ARAIBO- Team ARAIBO- CMPack' 00- CMPack '00- The Mcgill's Reddogs Legged League System- The McGill's RedDogs Legged League System- BabyTigers: Osaka Legged Robot Team- BabyTigers: Osaka Legged Robot Team- SPQR- SPQR- The University of Pennsylvania RoboCup Legged Soccer Team- The University of Pennsylvania RoboCup Legged Soccer Team- Team Sweden- Team Sweden- RoboMutts- RoboMutts- Humboldt Heroes- Humboldt Heroes

RoboCup 2000: Robot Soccer World Cup IV

Maneuvering target tracking of UAV based on MN-DDPG and transfer learning

According to various embodiments, a verification method may be provided. The verification method may include: determining a plurality of objects, each object having a property; displaying a representation of each object of the plurality of objects; receiving from a user an input indicating a sequence of the plurality of objects; determining a sequence of the properties of the plurality of objects; and comparing the Determine a plurality of objects, each object having a input with the sequence of the properties of the objects.

Verification methods and verification devices

We define b-compatibility for planar curves and propose three ball morphing techniques (b-morphs) between pairs of b-compatible curves. B-morphs use the automatic ball-map correspondence, proposed by Chazal et al. [12], from which they derive vertex trajectories (Linear, Circular, Parabolic). All are symmetric, meeting both curves with the same angle, which is a right angle for the Circular and Parabolic. We provide simple constructions for these b-morphs using the maximal disks in the finite region bounded by the two curves. We compare the b-morphs to each other and to other simple morphs (Linear Interpolation (LI), Closest Projection (CP), Curvature Interpolation (CI), Laplace Blending (LB), Heat Propagation (HP)) using seven measures of quality deficiency (travel distance, distortion, stretch, local acceleration, surface area, average curvature, maximal curvature). We conclude that the ratios of these measures depends heavily on the test case, especially for LI, CI, and LB, which compute correspondence from a uniform geodesic parameterization. Nevertheless, we found that the Linear b-morph has consistently the shortest travel distance and that the Circular b-morph has the least amount of distortion.

b-morphs between b-compatible curves in the plane

Recently, the International Commission on Radiological Protection (ICRP) developed new mesh-type reference computational phantoms (MRCPs) that provide high deformability compared with the current voxel-type reference computational phantoms of ICRP Publication 110. Taking advantage of this deformability, in the present study, the MRCPs were deformed to five non-standing postures (i.e. walking, sitting, bending, kneeling, and squatting) by developing and using a systematic posture-change method based on the as-rigid-as-possible (ARAP) shape-deformation algorithm and motion-capture technology. The non-standing MRCPs were then implemented in the Geant4 Monte Carlo code to calculate a comprehensive dataset of dose coefficients (DCs) for photon external exposures. These include the dose coefficients for 29 individual organs/tissues and the dose coefficients for effective doses from 0.01 MeV to 10 GeV in the antero-posterior (AP), postero-anterior (PA), left-lateral (LLAT), right-lateral (RLAT), rotational (ROT), and isotropic (ISO) geometries. To investigate the dosimetric impact of posture, the DCs of the non-standing MRCPs were compared with those of the original MRCPs (in the standing posture). The results showed that organ/tissue doses are significantly influenced by posture, with arm position mostly influencing dose to organs/tissues in the torso region and leg position influencing dose in the pelvic region. For most cases, the gonads showed notably large differences, ranging from a few tens of percentage points to several orders of magnitude, depending on posture and irradiation geometry. The effective doses showed much smaller differences than the organ/tissue doses, but they were nonetheless significant: for example, the kneeling MRCPs in the AP geometry showed lower values at energies  <10 MeV by up to 30% and greater values at higher energies by up to 40%. The presented results indicate that not only different irradiation geometries, but also different postures might be necessary in DC calculations for reliable dose estimates for radiological protection purposes.

https://iopscience.iop.org/article/10.1088/1361-6560/ab0917/pdf

Posture-dependent dose coefficients of mesh-type ICRP reference computational phantoms for photon external exposures.

As-rigid-as-possible shape deformation and interpolation

In real images, color recognition is a challenging problem because of natural variations in light and shadows. Most existing color models have limitations in distinctive representation of colors in real scenes. Here, a linear combination of multiple color models is assumed. The approach makes color edges in the target as main character for recognition. It combined multiple color models to make the recognition stable under varying imaging conditions. A proper weighting scheme to combine color spaces is obtained with the mathematical selection model of Markowitz, and the corresponding weights are obtained by multi-objective optimization. Effectiveness and reliability of the proposed method is demonstrated through various natural scene images.

A New Approach for Color-Based Object Recognition with Fusion of Color Models

Actor-critic method combines the fast convergence of value-based (critic) and directivity on search of policy gradient (actor). It is suitable for solving the problems with large state space. In this paper, the actor-critic method with tile-coding linear function approximation is analysed and applied to a RoboCup simulation subtask named "Soccer Keepaway". The experiments on Soccer Keepaway show that the policy learned by actor-critic method is better than policies from value-based Sarsa(lambda) and benchmarks

Research on Actor-Critic Reinforcement Learning in RoboCup

As the way of easing urban traffic congestion, taxi ridesharing can effectively protect the environment and solve the difficulty of passengers taking taxis when taxi demand is high. In this paper, we formally define the dynamic ride-sharing problem and propose a taxi candidates-reduction ride-sharing scheduling algorithm based on dynamic grid. Regarding the congestion situation of the multiple road condition, the concept of speed decay zone was purposed to simulate this area. To solve the problem of low satisfaction in the congested situation, we devise a dynamic grid division strategy that reduces the grid size of the hotspot area to satisfy the specific needs of passengers in rush hour, and efficiently screen candidate taxis by dynamic grid index. We perform the experiments using the request dataset generated by the taxi request simulator of Beijing Chaoyang district. The performance shows that our approach reduce 35.5% computation without losing average satisfaction compared with existing ridesharing algorithm.

Yuxin Wang

Papers

As-rigid-as-possible shape deformation and interpolation

A New Approach for Color-Based Object Recognition with Fusion of Color Models

Research on Actor-Critic Reinforcement Learning in RoboCup

A Dynamic Grid-Based Algorithm for Taxi Ridesharing in Multiple Road Condition

Research of RBAC model based on XML graph: Research of RBAC model based on XML graph