In real-world scenarios, the successful execution of an agent’s planned actions is not always guaranteed, as actions may fail in unpredictable ways that are not explicitly modeled. To address this challenge, the concept of Resilient Planning and the RESPLAN framework were introduced focusing on the generation of k-resilient plans that enable an agent to reach its goals even in the presence of up to k execution failures. In this paper, we propose a new version of the RESPLAN planning algorithm based on two significant enhancements. The first incorporates landmarks into a pruning strategy, enabling the planner to avoid unnecessary explorations and yielding substantial performance gains, especially when no resilient plan exists. The second introduces a planning adaptation strategy exploiting regressed state formulas to support the search process during (re)planning, reducing the number of iterations required when a resilient plan does exist. We compare our methods against RESPLAN and other baselines, demonstrating substantial improvements across multiple domains.

In the real world, the execution of the actions planned for an agent is never guaranteed to succeed, as they can fail in a number of unexpected ways that are not explicitly captured in the planning model. Based on these observations, we introduce the task of finding plans for classical planning that are resilient to action execution failures. We refer to this problem as Resilient Planning and to its solutions as K-resilient plans; such plans guarantee that an agent will always be able to reach its goals (possibly by replanning alternative sequences of actions) as long as no more than K failures occur along the way. We also present RESPLAN, a new algorithm for Resilient Planning, and we compare its performance to methods based on compiling Resilient Planning to Fully-Observable-Non-Deterministic (FOND) planning.

This article is to develop virtual reality-based framework for enhancing walking abilities using exoskeleton robotics. On one hand, China will face an ever-increasing and unprecedented demand for rehabilitation treatment and training for a long period of time in the future; on the other hand, backward and shortage of rehabilitation training resources urgently need to be rapidly upgraded through scientific and technological progress. A lightweight and intelligent system for indoor walking abilities rehabilitation training that combines virtual reality and exoskeleton robotics will effectively improve the rehabilitation training conditions, efficiency and effects through scientific and technological means. Through in-depth analysis and tracking of the training plan, combined with the research results of gait theory, the article describes a customized exoskeleton with VR glass and local cloud, and the sensing process, virtual scene establishment and presentation, human-robot interaction mechanism, virtual training and performance evaluation, and constraints are elaborated. Large-scale system testing and data collection and analysis, and the heterogeneity of rehabilitation training with this method will be the focus of future research.

This paper describes a method for designing an intelligent system to improve driver safety. A prototype of the system, which was designed by following this method, is presented. Driver physiological data acquired from sensors on the steering wheel are correlated, using statistical multivariate analysis, to the driver's vigilance level, which was evaluated using polysomnography. A driving simulation was conducted with a mechanical platform, whose data were also acquired and studied the same way. The parameters chosen for the evaluation of driver vigilance are used for the first time in such a system. Data are analyzed offline to set up a real-time driver vigilance controller. The data analysis results in one vigilance-level index for the current driver and situation.

This paper deals with the developed researches of biorobotics, as an instrument for the maintenance of the quality of human senses, complete control of the nervous system, activation of neuron circuits, recovery of damaged neuromotor functions, rehabilitation of vocal cords, and neuromotor system control following devastating diseases such as Parkinson's and Alzheimer's. An application of biorobotics is here presented: DDX is an experimental biorobotic system designed to acquire and provide data about human finger movement, applied in the analysis of neural disturbances with quantitative evaluation of both response times and dynamic action of the patient. The goal of the biorobotic system is to measure the response parameters of a person in front of a "soft touch", made by his finger in front of a button. It is now applied in daily clinical activity to diagnose the progression of the Parkinson pathology.

Deals with the developed researches and applications of telerobotic surgery. The paper outlines the following steps: (1) the execution of telesurgery robotic operation, using a satellite and a ISDN line as communication system; (2) the development of a telecontrol system used to remotely control a robotized system during the execution of a prostate biopsy on a human patient with a telerobotic system with optical fibers telecommunication; (3) the respect of normative for surgical robotics and surgical telerobotics in the hospitals and medical centers according to the European Normative (4) outline of some methods used in the telesurgical experiments developed at Politecnico di Milano to comply with the EU directives.

This paper deals with the description of a telerobotic surgery experiment, conducted on July 7, 1993, between the Politecnico di Milano, Telerobotics Laboratory, Italy, and the Jet Propulsion Laboratory, Pasadena, CA. It describes the results obtained, the new objectives proposed and the technical equipment. It also provides a comparison between the different solutions adopted. Telerobotic surgery requires particular skill; the integration of human capabilities with robotics in surgery offers useful results for robotic applications in new fields, especially health care.

An advanced graphic interface can be used for the modelling and simulation of an operation conducted by means of telerobotic surgery. The use of a graphic interface is justified in a telemanipulation system working under communication time delay. In fact the real time simulation allows an exploration of the future scenarios. It is also proved that the use of a virtual reality interface, with a graphic display, increases the performances of the operator. Laparoscopy is currently making a name for itself as one of the most interesting applications in the context of telerobotic surgery.

This paper deals with the evaluation of human biofeedback response in virtual reality and in direct view. The experiments have been performed with a new paradigm for the evaluation of human biofeedback during the telemanipulation performance of a touch task. The controlled motion of one finger is monitored with the surface EMG, while a mechanical robotized hand finger follows the motion imposed by the human finger. The biofeedback is detected in a direct way, by the vision of the robotized finger action, and in an indirect way, with the support of three different types of interfaces. The neuromuscular activity presents different features and delays in the four cases: A measurement of the attention and participation in the man/machine interface is obtained, in a first series of experiments. The paradigm adopted in this research is the result of the integration of robotics and neurology.>

This paper analyses human control performance by means of a telemanipulation system and measurements of muscular activity during teleoperations. The task is performed with the aid of different types of interfaces. The control loop of a telerobotic manipulation system includes the human motion program. The control strategy for human motion is closely dependent on the type of interface available, that is, on the way the performance knowledge is presented to the operator. The analysis here proposed concerns the sensory and logical evaluation of this dependence in a telerobotic application, by means of EMG signal acquisition during teleoperations both in real and virtual environments. The experiments have been performed with a new paradigm for the evaluation of human feedback during the telemanipulation performance of a touch task. The paradigm adopted in this research is the result of the integration of robotics and neurology.>

Research relating to robot self-planned trajectories is discussed. The study examines the generation of collision free trajectories between two points with minimum path times in the presence of polyhedral three-dimensional obstacles, for Cartesian robots. An analysis is included of the potential advantages to be obtained from parallel processing of the algorithms, which were developed.>

Deals with the design, modelling and construction of a prototype of a space telerobot for the rescue and recovery of astronauts in the area around a space station. The objective of the FRIEND robot project (an acronym of Flying Robot with Intelligently Ended Nursing Dexterity) is the testing of a telerobotised system controlled by a remote operator. The FRIEND robot is designed and constituted by a mechanical structure with two arms, an autonomous energy source, a sensor and motion control structure, a visual recognition system which acts as operator support, an expert intelligent system memorised in the computer for alternative choices in the stage of rescue and recovery of an astronaut in an emergency.>

The paper deals with the problems related to the implementation of an algorithm of planning of excellent trajectories for the arm of a Cartesian robot in the presence of an obstacle in the work field.>

Deals with the robot grasping manipulation by using fuzzy logic control system. The basic fuzzy control method for grasping is presented. The study of the grasped object, the grasping manipulation in a known environment and in an unknown environment are discussed. In the unknown environment the fuzzy control system shows intelligence that absorbs the human's operating experiences and thinking methods.>

This paper deals with the operation "assembly" meaned as logical complex operation, wich has the aim to create a structure, which is independent from the physical system on which the robot has to work. This logical structure allows the careful analysis of the robot's operative situations, the prevision of eventual negative facts which influence the movement activity, the generation of alternative situations and finally the acquisition of the auton omous decision by the control of the system. The strategy of the obstacles avoidance constitutes the first step in the construction of a supervisory structure of the robot's operativity by controlling the physical interactions with the environment and optimizing the behaviour as in the unfavourable cases.

This paper deals with the development of a sensor controlled robot hand for grasping objects of generic shape. The integration of control software and mechanical design may improve prehension quality performances.