김범준 교수

We propose a Learning from Demonstration (LfD) algorithm which leverages expert data, even if they are very few or inaccurate. We achieve this by using both expert data, as well as reinforcement signals gathered through trial-and-error interactions with the environment. The key idea of our approach, Approximate Policy Iteration with Demonstration (APID), is that expert's suggestions are used to define linear constraints which guide the optimization performed by Approximate Policy Iteration. We p

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called s

Imitation learning is an efficient method for many robots to acquire complex skills. Some recent approaches to imitation learning provide strong theoretical performance guarantees. However, there remain crucial practical issues, especially during the training phase, where the training strategy may require execution of control policies that are possibly harmful to the robot or its environment. Moreover, these algorithms often require more demonstrations than necessary to achieve good performance

In robotics, it is essential to be able to plan efficiently in high-dimensional continuous state-action spaces for long horizons. For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is hopelessly inefficient, and gradient-based approaches often fall short when the optimization manifold of a given problem is not smooth. In this paper, we present an approach that guides search in continuous spaces for generic planners by learning an action sampl

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called s

Many important applications, including robotics, data-center management, and process control, require planning action sequences in domains with continuous state and action spaces and discontinuous objective functions. Monte Carlo tree search (MCTS) is an effective strategy for planning in discrete action spaces. We provide a novel MCTS algorithm (voot) for deterministic environments with continuous action spaces, which, in turn, is based on a novel black-box function-optimization algorithm (voo)

We present a framework for learning to guide geometric task-and-motion planning (G-TAMP). G-TAMP is a subclass of task-and-motion planning in which the goal is to move multiple objects to target regions among movable obstacles. A standard graph search algorithm is not directly applicable, because G-TAMP problems involve hybrid search spaces and expensive action feasibility checks. To handle this, we introduce a novel planner that extends basic heuristic search with random sampling and a heuristi

There have been a lot of works to avoid retransmission timeout (RTO) of transmission control protocol (TCP) that takes place in an unnecessary situation. However, most current TCP implementations, even if selective acknowledgment (SACK) option is used, do not have a mechanism to detect a lost retransmission and avoid subsequent RTO. In this letter, we propose a simple modification that enables a TCP sender using SACK option to detect a lost retransmission, which is called TCP SACK+ in simple. We

We propose an actor-critic algorithm that uses past planning experience to improve the efficiency of solving robot task-and-motion planning (TAMP) problems. TAMP planners search for goal-achieving sequences of high-level operator instances specified by both discrete and continuous parameters. Our algorithm learns a policy for selecting the continuous parameters during search, using a small training set generated from the search trees of previously solved instances. We also introduce a novel fixe

The performance of transmission control protocol (TCP) is largely dependent upon its loss recovery. Therefore, it is a very important issue whether the packet losses may be recovered without retransmission timeout (RTO) or not. TCP always evokes RTO if a retransmitted packet is lost again. In order to alleviate this problem, we propose an algorithm called duplicate acknowledgment counting (DAC). We use a stochastic model to evaluate the performance of DAC, and compare it with TCP NewReno. Numeri

Unmanned Aerial Vehicles (UAVs) are abundantly becoming a part of society, which is a trend that is expected to grow even further. The quadrotor is one of the drone technologies that is applicable in many sectors and in both military and civilian activities, with some applications requiring autonomous flight. However, stability, path planning, and control remain significant challenges in autonomous quadrotor flights. Traditional control algorithms, such as proportional-integral-derivative (PID),

This paper covers the service quality of packet-based voice service that is provided over a wireless broadband (WiBro) network. Using a measurement software that has been developed in the course of preparing a advanced service quality management scheme for the packet-based voice service over a wireless network[2][3], a huge scale of experiment is conducted to measure the real quality of the voice service. Based on our analysis of the measurement result, the service quality of the voice service i