• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.266-273
• /
• 2024

With the rising interaction between robots and humans, detecting collisions has become increasingly vital for ensuring safety. In this paper, we propose a novel approach for detecting collisions without using force torque sensors or tactile sensors, utilizing a Transformer-based neural network architecture. The proposed collision detection approach comprises a torque estimator network that predicts the joint torque in a free-motion state using Synchronous time-step encoding, and a collision discriminator network that predicts collisions by leveraging the difference between estimated and actual torques. The collision discriminator finally creates a binary tensor that predicts collisions frame by frame. In simulations, the proposed network exhibited enhanced collision detection performance relative to the other kinds of networks both in terms of prediction speed and accuracy. This underscores the benefits of using Transformer networks for collision detection tasks, where rapid decision-making is essential.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.283-290
• /
• 2021

We propose a task and motion planning algorithm for clearing obstacles and wiping surfaces, which is essential for surface disinfection during the pathogen disinfection process. The proposed task and motion planning algorithm determines task parameters such as grasping pose and placement location during the planning process without using pre-specified or discretized values. Furthermore, to quickly inspect many unit motions, we propose a motion feasibility prediction algorithm consisting of collision checking and an SVM model for inverse mechanics and self-collision prediction. Planning time analysis shows that the feasibility prediction algorithm can significantly increase the planning speed and success rates in situations with multiple obstacles. Finally, we implemented a hierarchical control scheme to enable wiping motion while following a planner-generated joint trajectory. We verified our planning and control framework by conducted an obstacle-clearing and surface wiping experiment in a simulated disinfection environment.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.559-564
• /
• 2008

A prediction of binary droplets collision is important in the formation of falling drops and the evolution of sprays. The droplet velocity, impact parameter and drop-size ratio have influence on the interaction of the droplets. By the effect of these parameter, the collision processes are generated with the complicated phenomena. The droplet collision can be classified into four interactions such as the bouncing, coalescence, reflexive separation and stretching separation. In this study, the two-phase flow of the droplet collision was simulated numerically by using the Level Set method. 2D axi-symmetric simulations on the head-on collisions in the coalescence and reflexive separation, and 3D simulation on the off-center collisions in the coalescence and stretching separation were performed. These numerical results showed good agreements with the experimental and analytical results. For tracking the identity of droplets after the collision, transport equation for the volume fraction of the each initial droplet were used. From this, the identities of droplets were analyzed on the collision of droplets having different size.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1999-2004
• /
• 2004

Collision avoidance for the aircraft can be stated as a problem of maintaining a safe distance between aircrafts in conflict. Optimal collision avoidance problem seeks to minimize the given cost function while simultaneously satisfying the constraints. The cost function can be a function of time or input. This paper addresses the trajectory time-optimization problem for collision avoidance of the unmanned aerial vehicles. The problem is difficult to handle, because it is a two points boundary value problem with dynamic environment. Some simplifying algorithms are used for application in on-line operation. Although there are more complicated problems, by prediction of conflict time and some assumptions, we changed a dynamic environment problem into a static one.

• International Journal of Aeronautical and Space Sciences
• /
• v.5 no.2
• /
• pp.43-53
• /
• 2004

Collision avoidance for multiple aircraft can be stated as a problem ofmaintaining safe distance between aircraft in conflict. Optimal collision avoidanceproblem seeks to minimize the given cost function while simultaneously satisfyingconstraints. The cost function could be a function of time or control input. This paper addresses the trajectory time-optimization problem for collision avoidance of unmanned aerial vehicles(UAVs). The problem is difficult to handle in general due to the two-point boundary value problem subject to dynamic environments. Some simplifying aleorithms are used for potential applications in on-line operation.Although under possibility of more complicated problems, a dynamic problem is transformed into a static one by prediction of the conflict time and some appropriate assumptions.

• Design & Manufacturing
• /
• v.14 no.4
• /
• pp.40-45
• /
• 2020

In a vehicle-to-vehicle accident, the impact posture, braking status, final stopping position, collision point and collision speed are important factors for accident reconstruction. In particular, the speed of collision is the most important issue. In this study, the collision speed and the final stopping position in the tunnel were estimated using PC-CRASH, a vehicle crash analysis program used for traffic accident analysis, and the final stopping position of the simulation and the final stopping position of the traffic accident report were compared. When the Pride speed was 0km/h or 30km/h and the Sorento speed was 100m/h, the simulation results and reports matched the final stopping positions and posture of the two vehicles. As a result of the simulation, it can be estimated that Pride was collided in an almost stationary state.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.175-183
• /
• 2022

The collision between a ship and bridge across a waterway may result in extremely serious consequences that may endanger the safety of life and property. Therefore, factors affecting ship bridge collision must be investigated, and the impact force should be discussed based on various collision conditions. In this study, a finite element model of ship bridge collision is established, and the peak impact force of a ship bridge collision based on 50 operating conditions combined with three input parameters, i.e., ship loading condition, ship speed, and ship bridge collision angle, is calculated via numerical simulation. Using neural network models trained with the numerical simulation results, the prediction model of the peak impact force of ship bridge collision involving an extremely short calculation time on the order of milliseconds is established. The neural network models used in this study are the basic backpropagation neural network model and Elman neural network model, which can manage temporal information. The accuracy of the neural network models is verified using 10 test samples based on the operating conditions. Results of a verification test show that the Elman neural network model performs better than the backpropagation neural network model, with a mean relative error of 4.566% and relative errors of less than 5% in 8 among 10 test cases. The trained neural network can yield a reliable ship bridge collision force instantaneously only when the required parameters are specified and a nonlinear finite element solution process is not required. The proposed model can be used to predict whether a catastrophic collision will occur during ship navigation, and thus hence the safety of crew operating the ship.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.255-261
• /
• 2008

RFID(Radio Frequency IDentification) is a technology that automatically identifies objects containing the electronic tags by using radio frequency. In RFID system, the reader needs the anti collision algorithm for fast identifring all of the tags in the interrogation zone. This Paper proposes the tree based TPAE(Tag Prediction Algorithm using Extra bit) algorithm to arbitrate the tag collision. The proposed algorithm can identify tags without identifring all the bits in the tag ID. The reader uses the extra bit which is added to the tag ID and if there are two collided bits or multiple collided bits, it checks the extra bit and grasps the tag IDs concurrently. In the experiment, the proposed algorithm had about 50% less query iterations than query tree algorithm and binary search algorithm regardless of the number of tags and tag ID lengths.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.1048-1052
• /
• 2013

Recently, many countries have attempted to protect their satellites from damage caused by space debris. To design these collision avoidance maneuvers, optimal algorithms based on numerical simulations are widely used due to their practicality. However, these algorithms often require a great expenditure of time in order to find solutions. Therefore, in this paper, a simple analytical strategy is suggested to find the initial prediction required to find these numerical solutions for collision avoidance maneuvers by using relative dynamics for the rendezvous and docking problems. For this analytical strategy, the simple dynamics on the CW (Clohessy-Wiltshire) frame is adopted as an attempt to introduce an analytical solution.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.11
• /
• pp.3997-4015
• /
• 2014

Radio frequency identification (RFID) is an emerging wireless communication technology which allows objects to be identified automatically. The tag anti-collision is a significant issue for fast identifying tags due to the shared wireless channel between tags and the reader during communication. The EPCglobal Class-1 Generation-2 which uses Q algorithm for the anti-collision is widely used in many applications such as consumer electronic device and supply chain. However, the increasing application of EPCglobal Class-1 Generation-2 which requires the dynamic environment makes the efficiency decrease critically. Furthermore, its frame length (size) determination and frame termination lead to the suboptimal efficiency. A new anti-collision algorithm is proposed to deal with the two problems for large-scale RFID systems. The algorithm has higher performance than the Q algorithm in the dynamic environment. Some simulations are given to illustrate the performance.