scholarly journals HyP-DESPOT: A hybrid parallel algorithm for online planning under uncertainty

2020 ◽  
pp. 027836492093707
Author(s):  
Panpan Cai ◽  
Yuanfu Luo ◽  
David Hsu ◽  
Wee Sun Lee
Keyword(s):  
Real Time ◽  
Computational Cost ◽  
Search Tree ◽  
Planning Under Uncertainty ◽  
State Action ◽  
Online Planning ◽  
Planning Algorithm ◽  
One Step ◽  
Robotic Tasks ◽  
High Computational Cost

Robust planning under uncertainty is critical for robots in uncertain, dynamic environments, but incurs high computational cost. State-of-the-art online search algorithms, such as DESPOT, have vastly improved the computational efficiency of planning under uncertainty and made it a valuable tool for robotics in practice. This work takes one step further by leveraging both CPU and GPU parallelization in order to achieve real-time online planning performance for complex tasks with large state, action, and observation spaces. Specifically, Hybrid Parallel DESPOT (HyP-DESPOT) is a massively parallel online planning algorithm that integrates CPU and GPU parallelism in a multi-level scheme. It performs parallel DESPOT tree search by simultaneously traversing multiple independent paths using multi-core CPUs; it performs parallel Monte Carlo simulations at the leaf nodes of the search tree using GPUs. HyP-DESPOT provably converges in finite time under moderate conditions and guarantees near-optimality of the solution. Experimental results show that HyP-DESPOT speeds up online planning by up to a factor of several hundred in several challenging robotic tasks in simulation, compared with the original DESPOT algorithm. It also exhibits real-time performance on a robot vehicle navigating among many pedestrians.

An Alternate Algorithm for (3x3) Median Filtering of Digital Images

2012 ◽  
Vol 2 (1) ◽  
pp. 7-9 ◽  
Author(s):  
Satinderjit Singh
Keyword(s):  
Median Filter ◽  
Computational Cost ◽  
Spatial Coherence ◽  
General Purpose ◽  
Median Filtering ◽  
Basic Algorithm ◽  
Temporal Complexity ◽  
Filter Kernel ◽  
One Step ◽  
High Computational Cost

Median filtering is a commonly used technique in image processing. The main problem of the median filter is its high computational cost (for sorting N pixels, the temporal complexity is O(N·log N), even with the most efficient sorting algorithms). When the median filter must be carried out in real time, the software implementation in general-purpose processorsdoes not usually give good results. This Paper presents an efficient algorithm for median filtering with a 3x3 filter kernel with only about 9 comparisons per pixel using spatial coherence between neighboring filter computations. The basic algorithm calculates two medians in one step and reuses sorted slices of three vertical neighboring pixels. An extension of this algorithm for 2D spatial coherence is also examined, which calculates four medians per step.

Algorithm of Rational Planning and Resource Distribution in the Task of Preparing the Aircraft Group for Use

2019 ◽  
Vol 20 (5) ◽  
pp. 314-320
Author(s):  
Yu. I. Buryak ◽  
A. A. Screennikov
Keyword(s):  
High Speed ◽  
Discrete Event ◽  
Computational Cost ◽  
Admissible Solution ◽  
Event Modeling ◽  
Rational Planning ◽  
Planning Algorithm ◽  
Computational Resources ◽  
High Computational Cost ◽  
Rational Composition

The work is devoted to solving the problem of justifying the rational composition of a team of specialists who provide preparing for a group of aircraft for a given time. To substantiate the optimal composition of the team, it is necessary to solve the problem of scheduling work on a group of aircraft with different composition of specialists. This, in turn, requires consideration of the huge number of options for streamlining work performed on each aircraft, and options for organizing the sequence of maintenance by one specialist of several aircraft. Finding solutions using combinatorial optimization requires an unacceptably high computational cost. The article proposes an approach for finding not the optimal, but some rational admissible solution, which is not much worse than the optimal one, but its definition does not require large computational resources. An algorithm for rational work scheduling based on discrete-event modeling is proposed. Planning is carried out sequentially in time. When planning the sequence of work, it was suggested first of all to put the work with the maximum duration possible. The developed algorithm is software implemented, which allowed to investigate some properties of the solutions obtained. Examples of calculating the schedule of work on a group of aircraft with a different composition of the team of specialists are given. The problem of justification of rational structure of the team is solved by rational planning algorithm works by sequentially increasing the number of specialists. An example of substantiating the rational composition of a team of specialists performing preparing of a group of eight aircraft, each of which performs five types of work, is given and analyzed in details. The high speed of the calculations for the rational planning of work by a given team allowed to consider all possible options for the team (tens of thousands of options) and substantiate such an option that the number of specialists in the team would be minimal, but they would ensure the preparation of aircraft for a given time. Low requirements for computing resources allow solving problems with a sufficiently large number of types of work performed on each aircraft of the group.

Importance sampling for online planning under uncertainty

2018 ◽  
Vol 38 (2-3) ◽  
pp. 162-181 ◽  
Author(s):  
Yuanfu Luo ◽  
Haoyu Bai ◽  
David Hsu ◽  
Wee Sun Lee
Keyword(s):  
Importance Sampling ◽  
Autonomous Vehicles ◽  
State Of The Art ◽  
Monte Carlo Sampling ◽  
Planning Under Uncertainty ◽  
Online Planning ◽  
Markov Decision ◽  
Partially Observable ◽  
Robotic Tasks ◽  
General Method

The partially observable Markov decision process (POMDP) provides a principled general framework for robot planning under uncertainty. Leveraging the idea of Monte Carlo sampling, recent POMDP planning algorithms have scaled up to various challenging robotic tasks, including, real-time online planning for autonomous vehicles. To further improve online planning performance, this paper presents IS-DESPOT, which introduces importance sampling to DESPOT, a state-of-the-art sampling-based POMDP algorithm for planning under uncertainty. Importance sampling improves DESPOT’s performance when there are critical, but rare events, which are difficult to sample. We prove that IS-DESPOT retains the theoretical guarantee of DESPOT. We demonstrate empirically that importance sampling significantly improves the performance of online POMDP planning for suitable tasks. We also present a general method for learning the importance sampling distribution.

scholarly journals Real-Time Haze Removal Using Normalised Pixel-Wise Dark-Channel Prior and Robust Atmospheric-Light Estimation

2020 ◽  
Vol 10 (3) ◽  
pp. 1165 ◽  
Author(s):  
Yutaro Iwamoto ◽  
Naoaki Hashimoto ◽  
Yen-Wei Chen
Keyword(s):  
Real Time ◽  
Computational Cost ◽  
Dark Channel Prior ◽  
Detailed Structure ◽  
Haze Removal ◽  
Acceptable Quality ◽  
Colour Channel ◽  
Dark Channel ◽  
High Computational Cost ◽  
Atmospheric Light

This study proposes real-time haze removal from a single image using normalised pixel-wise dark-channel prior (DCP). DCP assumes that at least one RGB colour channel within most local patches in a haze-free image has a low-intensity value. Since the spatial resolution of the transmission map depends on the patch size and it loses the detailed structure with large patch sizes, original work refines the transmission map using an image-matting technique. However, it requires high computational cost and is not adequate for real-time application. To solve these problems, we use normalised pixel-wise haze estimation without losing the detailed structure of the transmission map. This study also proposes robust atmospheric-light estimation using a coarse-to-fine search strategy and down-sampled haze estimation for acceleration. Experiments with actual and simulated haze images showed that the proposed method achieves real-time results of visually and quantitatively acceptable quality compared with other conventional methods of haze removal.

scholarly journals A Framework for Real-Time 3D Freeform Manipulation of Facial Video

2019 ◽  
Vol 9 (21) ◽  
pp. 4707
Author(s):  
Jungsik Park ◽  
Byung-Kuk Seo ◽  
Jong-Il Park
Keyword(s):  
Real Time ◽  
Computational Cost ◽  
Video Frame ◽  
Face Model ◽  
Live Video ◽  
Time Performance ◽  
Face Region ◽  
3D Manipulation ◽  
Comparison Results ◽  
High Computational Cost

This paper proposes a framework that allows 3D freeform manipulation of a face in live video. Unlike existing approaches, the proposed framework provides natural 3D manipulation of a face without background distortion and interactive face editing by a user’s input, which leads to freeform manipulation without any limitation of range or shape. To achieve these features, a 3D morphable face model is fitted to a face region in a video frame and is deformed by the user’s input. The video frame is then mapped as a texture to the deformed model, and the model is rendered on the video frame. Because of the high computational cost, parallelization and acceleration schemes are also adopted for real-time performance. Performance evaluation and comparison results show that the proposed framework is promising for 3D face editing in live video.

Health Aware Planning Under Uncertainty for Collaborating Heterogeneous Teams of Mobile Agents

2015 ◽  
Vol 03 (02) ◽  
pp. 89-107 ◽  
Author(s):  
N. Kemal Ure ◽  
Girish Chowdhary ◽  
Jonathan P. How ◽  
John Vian
Keyword(s):  
Large Scale ◽  
Planning Under Uncertainty ◽  
Potential Health ◽  
Adaptive Controllers ◽  
State Action ◽  
State Dependent ◽  
Long Duration ◽  
Markov Decision ◽  
Comprehensive Health ◽  
Planning Algorithm

We consider the problem of solving hybrid discrete-continuous Markov Decision Processes (MDPs) that are often encountered in computing optimal policies for complex multi-agent missions with both continuous vehicle dynamics and discrete mission-state transition models, in the presence of potential health degradations and failures of individual agents. A comprehensive Health Aware Planning (HAP) framework is proposed that establishes a feedback between mission planning and vehicle-level learning-focused adaptive controllers through online learned own models of agent health and capabilities. The HAP framework accounts for predicted likelihood of vehicle health degradations captured through probabilistic state-dependent models that are integrated into the MDP formulation. This proactive ability to anticipate health degradation and plan accordingly enables the HAP approach to consistently outperform planners that change the policies only after failures have occurred (reactive planners). The approach is tested on a large-scale (≈ 1010 state–action pairs) long-duration (persistent) target tracking scenario using a novel on-trajectory planning algorithm, and demonstrated to sustain higher mission performance by reducing the number of failures and re-assessing Unmanned Aerial Vehicle (UAV) capabilities.

scholarly journals Proposta de Implementação em Hardware do Algoritmo de Otsu Aplicado ao Rastreamento em Tempo Real de Vermes

2021 ◽  
Author(s):  
Wysterlânya Kyury Pereira Barros ◽  
Marcelo Fernandes
Keyword(s):  
Rna Interference ◽  
High Resolution ◽  
Real Time ◽  
Computational Cost ◽  
Field Programmable ◽  
Otsu’S Method ◽  
Real Time Tracking ◽  
Global Thresholding ◽  
Thresholding Algorithm ◽  
High Computational Cost

This work proposes an implementation in Field Programmable GateArray (FPGA) of the Otsu’s method applied to real-time trackingof worms called Caenorhabditis elegans. Real-time tracking is necessaryto measure changes in the worm’s behavior in response totreatment with Ribonucleic Acid (RNA) interference. Otsu’s methodis a global thresholding algorithm used to define an optimal thresholdbetween two classes. However, this technique in real-time applicationsassociated with the processing of high-resolution videoshas a high computational cost because of the massive amount ofdata generated. Otsu’s algorithm needs to identify the worms ineach frame captured by a high-resolution camera in a real-timeanalysis of the worm’s behavior. Thus, this work proposes a highperformanceimplementation of Otsu’s algorithm in FPGA. Theresults show it was possible to achieve a speedup up to 5 timeshigher than similar works in the literature.

scholarly journals DESPOT: Online POMDP Planning with Regularization

2017 ◽  
Vol 58 ◽  
pp. 231-266 ◽  
Author(s):  
Nan Ye ◽  
Adhiraj Somani ◽  
David Hsu ◽  
Wee Sun Lee
Keyword(s):  
Autonomous Driving ◽  
Vehicle Control ◽  
Planning Under Uncertainty ◽  
Driving System ◽  
Online Planning ◽  
Markov Decision ◽  
Planning Algorithm ◽  
Regret Bound ◽  
Partially Observable ◽  
Autonomous Driving System

The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the "curse of dimensionality" and the "curse of history". To overcome these challenges, we introduce the Determinized Sparse Partially Observable Tree (DESPOT), a sparse approximation of the standard belief tree, for online planning under uncertainty. A DESPOT focuses online planning on a set of randomly sampled scenarios and compactly captures the "execution" of all policies under these scenarios. We show that the best policy obtained from a DESPOT is near-optimal, with a regret bound that depends on the representation size of the optimal policy. Leveraging this result, we give an anytime online planning algorithm, which searches a DESPOT for a policy that optimizes a regularized objective function. Regularization balances the estimated value of a policy under the sampled scenarios and the policy size, thus avoiding overfitting. The algorithm demonstrates strong experimental results, compared with some of the best online POMDP algorithms available. It has also been incorporated into an autonomous driving system for real-time vehicle control. The source code for the algorithm is available online.

scholarly journals Real-Time Collision-Free Navigation of Multiple UAVs Based on Bounding Boxes

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1632
Author(s):  
Paloma Sánchez ◽  
Rafael Casado ◽  
Aurelio Bermúdez
Keyword(s):  
Real Time ◽  
Collision Avoidance ◽  
Computational Cost ◽  
Multiple Uavs ◽  
Navigation Algorithms ◽  
Excellent Candidate ◽  
Bounding Boxes ◽  
Velocity Obstacle ◽  
High Computational Cost ◽  
Multi Uav

Predictably, future urban airspaces will be crowded with autonomous unmanned aerial vehicles (UAVs) offering different services to the population. One of the main challenges in this new scenario is the design of collision-free navigation algorithms to avoid conflicts between flying UAVs. The most appropriate collision avoidance strategies for this scenario are non-centralized ones that are dynamically executed (in real time). Existing collision avoidance methods usually entail a high computational cost. In this work, we present Bounding Box Collision Avoidance (BBCA) algorithm, a simplified velocity obstacle-based technique that achieves a balance between efficiency and cost. The performance of the proposal is analyzed in detail in different airspace configurations. Simulation results show that the method is able to avoid all the conflicts in two UAV scenarios and most of them in multi-UAV ones. At the same time, we have found that the penalty of using the BBCA collision avoidance technique on the flying time and the distance covered by the UAVs involved in the conflict is reasonably acceptable. Therefore, we consider that BBCA may be an excellent candidate for the design of collision-free navigation algorithms for UAVs.

Sign in / Sign up

Export Citation Format

Share Document