scholarly journals Multi-Sensor Perception Strategy to Enhance Autonomy of Robotic Operation for Uncertain Peg-in-Hole Task

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3818
Author(s):  
Li Qin ◽  
Hongyu Wang ◽  
Yazhou Yuan ◽  
Shufan Qin
Keyword(s):  
Particle Filtering ◽  
Probabilistic Models ◽  
Evidence Theory ◽  
Target Position ◽  
Object Perception ◽  
Monte Carlo Sampling ◽  
Decision Strategy ◽  
Visual Occlusion ◽  
Object Feature ◽  
Robot Task

The peg-in-hole task with object feature uncertain is a typical case of robotic operation in the real-world unstructured environment. It is nontrivial to realize object perception and operational decisions autonomously, under the usual visual occlusion and real-time constraints of such tasks. In this paper, a Bayesian networks-based strategy is presented in order to seamlessly combine multiple heterogeneous senses data like humans. In the proposed strategy, an interactive exploration method implemented by hybrid Monte Carlo sampling algorithms and particle filtering is designed to identify the features' estimated starting value, and the memory adjustment method and the inertial thinking method are introduced to correct the target position and shape features of the object respectively. Based on the Dempster–Shafer evidence theory (D-S theory), a fusion decision strategy is designed using probabilistic models of forces and positions, which guided the robot motion after each acquisition of the estimated features of the object. It also enables the robot to judge whether the desired operation target is achieved or the feature estimate needs to be updated. Meanwhile, the pliability model is introduced into repeatedly perform exploration, planning and execution steps to reduce interaction forces, the number of exploration. The effectiveness of the strategy is validated in simulations and in a physical robot task.

scholarly journals Object-Feature Binding Survives Dynamic Shifts of Spatial Attention

2019 ◽  
Vol 30 (3) ◽  
pp. 343-361 ◽  
Author(s):  
Emma Wu Dowd ◽  
Julie D. Golomb
Keyword(s):  
Spatial Attention ◽  
Probabilistic Models ◽  
Target Item ◽  
Object Perception ◽  
Feature Binding ◽  
Visual Object ◽  
Multiple Features ◽  
Total N ◽  
Object Feature ◽  
Single Focus

Visual object perception requires integration of multiple features; spatial attention is thought to be critical to this binding. But attention is rarely static—how does dynamic attention impact object integrity? Here, we manipulated covert spatial attention and had participants (total N = 48) reproduce multiple properties (color, orientation, location) of a target item. Object-feature binding was assessed by applying probabilistic models to the joint distribution of feature errors: Feature reports for the same object could be correlated (and thus bound together) or independent. We found that splitting attention across multiple locations degrades object integrity, whereas rapid shifts of spatial attention maintain bound objects. Moreover, we document a novel attentional phenomenon, wherein participants exhibit unintentional fluctuations— lapses of spatial attention—yet nevertheless preserve object integrity at the wrong location. These findings emphasize the importance of a single focus of spatial attention for object-feature binding, even when that focus is dynamically moving across the visual field.

Efficient estimation and ensemble generation in climate modelling

2007 ◽  
Vol 365 (1857) ◽  
pp. 2077-2088 ◽  
Author(s):  
J.D Annan ◽  
J.C Hargreaves
Keyword(s):  
Monte Carlo ◽  
Particle Filtering ◽  
General Circulation ◽  
Climate Models ◽  
General Circulation Models ◽  
Monte Carlo Sampling ◽  
Efficient Estimation ◽  
Future Research ◽  
Great Promise ◽  
Climate Modelling

In this paper, we review progress towards efficiently estimating parameters in climate models. Since the general problem is inherently intractable, a range of approximations and heuristic methods have been proposed. Simple Monte Carlo sampling methods, although easy to implement and very flexible, are rather inefficient, making implementation possible only in the very simplest models. More sophisticated methods based on random walks and gradient-descent methods can provide more efficient solutions, but it is often unclear how to extract probabilistic information from such methods and the computational costs are still generally too high for their application to state-of-the-art general circulation models (GCMs). The ensemble Kalman filter is an efficient Monte Carlo approximation which is optimal for linear problems, but we show here how its accuracy can degrade in nonlinear applications. Methods based on particle filtering may provide a solution to this problem but have yet to be studied in any detail in the realm of climate models. Statistical emulators show great promise for future research and their computational speed would eliminate much of the need for efficient sampling techniques. However, emulation of a full GCM has yet to be achieved and the construction of such represents a substantial computational task in itself.

Decision-Making Under Model Uncertainty of Damaged Aircraft Systems

2009 ◽  
Author(s):  
Israel Lopez ◽  
Nesrin Sarigul-Klijn
Keyword(s):  
Decision Making ◽  
Motion Planning ◽  
Trajectory Planning ◽  
Evidence Theory ◽  
Target Position ◽  
Landing Site ◽  
Assessment Process ◽  
Diagnosis And Prognosis ◽  
Human Decision ◽  
Aircraft Trajectory

When in-flight failures occur, rapid and precise decision-making under imprecise information is required in order to regain and maintain control of the aircraft. To achieve planned aircraft trajectory and complete landing safely, the uncertainties in vehicle parameters of the damaged aircraft need to be learned and incorporated at the level of motion planning. Uncertainty is a very important concern in recovery of damaged aircraft since it can cause false diagnosis and prognosis that may lead to further performance degradation and mission failure. The mathematical and statistical approaches to analyzing uncertainty are first presented. The damaged aircraft is simulated via a simplified kinematics model. The different sources and perspectives of uncertainties under a damage assessment process and post-failure trajectory planning are presented and classified. The decision-making process for an emergency motion planning to landing site is developed via the Dempster-Shafer evidence theory. The objective of the trajectory planning is to arrive at a target position while maximizing the safety of the aircraft under uncertain conditions. Simulations are presented for an emergency motion planning and landing that takes into account aircraft dynamics, path complexity, distance to landing site, runway characteristics, and subjective human decision.

scholarly journals Sensorimotor delays in tracking may be compensated by negative feedback control of motion-extrapolated position

2020 ◽  
Author(s):  
Maximilian G. Parker ◽  
Andrew P. Weightman ◽  
Sarah F. Tyson ◽  
Bruce Abbott ◽  
Warren Mansell
Keyword(s):  
Feedback Control ◽  
Negative Feedback ◽  
Computational Models ◽  
Probabilistic Models ◽  
Position Control ◽  
Target Position ◽  
Extrapolation Model ◽  
Negative Feedback Control ◽  
The Difference ◽  
Parsimonious Model

Abstract Sensorimotor delays dictate that humans act on outdated perceptual information. As a result, continuous manual tracking of an unpredictable target incurs significant response delays. However, no such delays are observed for repeating targets such as the sinusoids. Findings of this kind have led researchers to claim that the nervous system constructs predictive, probabilistic models of the world. However, a more parsimonious explanation is that visual perception of a moving target position is systematically biased by its velocity. The resultant extrapolated position could be compared with the cursor position and the difference canceled by negative feedback control, compensating sensorimotor delays. The current study tested whether a position extrapolation model fit human tracking of sinusoid (predictable) and pseudorandom (less predictable) targets better than the non-biased position control model, Twenty-eight participants tracked these targets and the two computational models were fit to the data at 60 fixed loop delay values (simulating sensorimotor delays). We observed that pseudorandom targets were tracked with a significantly greater phase delay than sinusoid targets. For sinusoid targets, the position extrapolation model simulated tracking results more accurately for loop delays longer than 120 ms, thereby confirming its ability to compensate for sensorimotor delays. However, for pseudorandom targets, this advantage arose only after 300 ms, indicating that velocity information is unlikely to be exploited in this way during the tracking of less predictable targets. We conclude that negative feedback control of position is a parsimonious model for tracking pseudorandom targets and that negative feedback control of extrapolated position is a parsimonious model for tracking sinusoidal targets.

scholarly journals Probabilistic Prognosis with Dynamic Bayesian Networks

2020 ◽  
Vol 6 (4) ◽  
Author(s):  
Gregory Bartram ◽  
Sankaran Mahadevan
Keyword(s):  
Bayesian Networks ◽  
Particle Filtering ◽  
Dynamic Bayesian Network ◽  
Monte Carlo Sampling ◽  
Dynamic Bayesian Networks ◽  
Hydraulic Actuator ◽  
Current Estimate ◽  
Seamless Integration ◽  
State Estimate ◽  
System Variables

This paper proposes a methodology for probabilistic prognosis of a system using a dynamic Bayesian network (DBN). Dynamic Bayesian networks are suitable for probabilistic prognosis because of their ability to integrate information in a variety of formats from various sources and give a probabilistic representation of the system state. Further, DBNs provide a platform naturally suited for seamless integration of diagnosis, uncertainty quantification, and prediction. In the proposed methodology, a DBN is used for online diagnosis via particle filtering, providing a current estimate of the joint distribution over the system variables. The information available in the state estimate also helps to quantify the uncertainty in diagnosis. Next, based on this probabilistic state estimate, future states of the system are predicted using the DBN and sequential or recursive Monte Carlo sampling. Prediction in this manner provides the necessary information to estimate the distribution of remaining use life (RUL). The prognosis procedure, which is system specific, is validated using a suite of offline hierarchical metrics. The prognosis methodology is demonstrated on a hydraulic actuator subject to a progressive seal wear that results in internal leakage between the chambers of the actuator.

scholarly journals Monte Carlo Sampling Methods for Approximating Interactive POMDPs

2009 ◽  
Vol 34 ◽  
pp. 297-337 ◽  
Author(s):  
P. Doshi ◽  
P. J Gmytrasiewicz
Keyword(s):  
Particle Filtering ◽  
Belief Systems ◽  
Single Agent ◽  
Approximate Solutions ◽  
Monte Carlo Sampling ◽  
Physical World ◽  
Space Complexity ◽  
Policy Space ◽  
Complementary Method ◽  
Look Ahead

Partially observable Markov decision processes (POMDPs) provide a principled framework for sequential planning in uncertain single agent settings. An extension of POMDPs to multiagent settings, called interactive POMDPs (I-POMDPs), replaces POMDP belief spaces with interactive hierarchical belief systems which represent an agent’s belief about the physical world, about beliefs of other agents, and about their beliefs about others’ beliefs. This modification makes the difficulties of obtaining solutions due to complexity of the belief and policy spaces even more acute. We describe a general method for obtaining approximate solutions of I-POMDPs based on particle filtering (PF). We introduce the interactive PF, which descends the levels of the interactive belief hierarchies and samples and propagates beliefs at each level. The interactive PF is able to mitigate the belief space complexity, but it does not address the policy space complexity. To mitigate the policy space complexity – sometimes also called the curse of history – we utilize a complementary method based on sampling likely observations while building the look ahead reachability tree. While this approach does not completely address the curse of history, it beats back the curse’s impact substantially. We provide experimental results and chart future work.

Hybrid Probabilistic Models of Fuzzy and Rough Events

2003 ◽  
Vol 7 (3) ◽  
pp. 322-329
Author(s):  
Rolly Intan ◽  
◽  
Masao Mukaidono ◽  
Hung T. Nguyen ◽  
◽  
...  
Keyword(s):  
Conditional Probability ◽  
Rough Set ◽  
Fuzzy Set ◽  
Probabilistic Models ◽  
Evidence Theory ◽  
Probability Measures ◽  
The Relationship

This paper discusses the relationship between probability and fuzziness based on the process of perception. As a generalization of the crisp set, the fuzzy set is used to model fuzzy events as proposed by Zadeh. Similarly, we may consider the rough set to represent a rough event in terms of probability measures. Special attention will be given to conditional probability of fuzzy events as well as the conditional probability of rough events. Several combinations of formulation and properties are examined. In the relation to evidence theory, the probability of a rough event may be considered as a connecting bridge between belief-plausibility measures and the probability measures. Moreover, a generalized fuzzy-rough event is introduced to generalize both fuzzy and rough events.

The Influence of Premovement Visual Information on Manual Aiming

1987 ◽  
Vol 39 (3) ◽  
pp. 541-559 ◽  
Author(s):  
Digby Elliott ◽  
John Madalena
Keyword(s):  
Visual Information ◽  
Visual Representation ◽  
Target Position ◽  
Movement Control ◽  
Manual Aiming ◽  
Delay Effect ◽  
Movement Initiation ◽  
Pointing Error ◽  
Visual Occlusion ◽  
Small Targets

Three experiments were conducted to determine whether a visual representation of the movement environment, useful for movement control, exists after visual occlusion. In Experiment 1 subjects moved a stylus to small targets in five different visual conditions. As in other studies (e.g. Elliott and Allard, 1985), subjects moved to the targets in a condition involving full visual information (lights on) and a condition in which the lights were extinguished upon movement initiation (lights off). Subjects also pointed to the targets under conditions in which the lights went off 2, 5 and 10 sec prior to movement initiation. While typical lights-on-lights-off differences in accuracy were obtained in this experiment (Keele and Posner, 1968), the more striking finding was the influence of the pointing delay on movement accuracy. Specifically, subjects exhibited a twofold increase in pointing error after only 2 sec of visual occlusion prior to movement initiation. In Experiment 2, we were able to replicate our 2-sec pointing delay effect with a between-subjects design, providing evidence that the results in Experiment 1 were not due to asymmetrical transfer effects. In a third experiment, the delay effect was reduced by making the target position visible in all lights-off situations. Together, the findings provide evidence for the existence of a brief (< 2 sec) visual representation of the environment useful in the control of aiming movements.

Sign in / Sign up

Export Citation Format

Share Document