Semantic grasping: planning task-specific stable robotic grasps

We present an example-based planning framework to generate semantic grasps, stable grasps that are functionally suitable for specific object manipulation tasks. We propose to use partial object geometry, tactile contacts, and hand kinematic data as proxies to encode task-related constraints, which we call semantic constraints. We introduce a semantic affordance map, which relates local geometry to a set of predefined semantic grasps that are appropriate to different tasks. Using this map, the pose of a robot hand with respect to the object can be estimated so that the hand is adjusted to achieve the ideal approach direction required by a particular task. A grasp planner is then used to search along this approach direction and generate a set of final grasps which have appropriate stability, tactile contacts, and hand kinematics. We show experiments planning semantic grasps on everyday objects and applying these grasps with a physical robot.     

Path planning of wheeled mobile robot with simultaneous free space locating capability

This paper presents a hybrid path planning algorithm for the design of autonomous vehicles such as mobile robots. The hybrid planner is based on Potential Field method and Voronoi Diagram approach and is represented with the ability of concurrent navigation and map building. The system controller (Look-ahead Control) with the Potential Field method guarantees the robot generate a smooth and safe path to an expected position. The Voronoi Diagram approach is adopted for the purpose of helping the mobile robot to avoid being trapped by concave environment while exploring a route to a target. This approach allows the mobile robot to accomplish an autonomous navigation task with only an essential exploration between a start and goal position. Based on the existing topological map the mobile robot is able to construct sub-goals between predefined start and goal, and follows a smooth and safe trajectory in a flexible manner when stationary and moving obstacles co-exist.     

Fuzzy Logic Based Behavior Fusion for Navigation of an Intelligent Mobile Robot

This paper presents a new method for behavior fusion control of a mobile robot in uncertain environments.Using behavior fusion by fuzzy logic,a mobile robot is able to directly execute its motion according to range information about environments,acquired by ultrasonic sensors,without the need for trajectory planning.Based on low-level behavior control,an efficient strategy for integrating high-level global planning for robot motion can be formulated,since,in most applications,some information on environments is prior knowledge.A global planner,therefore,only to generate some subgoal positions rather than exact geometric paths.Because such subgoals can be easily removed from or added into the plannes,this strategy reduces computational time for global planning and is flexible for replanning in dynamic environments.Simulation results demonstrate that the proposed strategy can be applied to robot motion in complex and dynamic environments.     

Planning the motions of a mobile robot in a sensory uncertaintyfield

Failures in mobile robot navigation are often caused by errors in localizing the robot relative to its environment. This paper explores the idea that these errors can be considerably reduced by planning paths taking the robot through positions where pertinent features of the environment can be sensed. It introduces the notion of a “sensory uncertainty field” (SUF). For every possible robot configuration q, this field estimates the distribution of possible errors in the robot configuration that would be computed by a localization function matching the data given by the sensors against an environment model, if the robot was at q. A planner is proposed which uses a precomputed SUF to generate paths that minimize expected errors or any other criterion combining, say, path length and errors. This paper describes in detail the computation of a specific SUF for a mobile robot equipped with a classical line-striping camera/laser range sensor. It presents an implemented SUF-based motion planner for this robot and shows paths generated by this planner. Navigation experiments were conducted with mobile robots using paths generated by the SUF-based planner and other paths. The former paths were tracked with greater precision than the others. The final section of the paper discusses additional research issues related to SUF-based planning     

Recognition, prediction, and planning for assisted teleoperation of freeform tasks

The approach of inferring user’s intended task and optimizing low-level robot motions has promise for making robot teleoperation interfaces more intuitive and responsive. But most existing methods assume a finite set of candidate tasks, which limits a robot’s functionality. This paper proposes the notion of freeform tasks that encode an infinite number of possible goals (e.g., desired target positions) within a finite set of types (e.g., reach, orient, pick up). It also presents two technical contributions to help make freeform UIs possible. First, an intent predictor estimates the user’s desired task, and accepts freeform tasks that include both discrete types and continuous parameters. Second, a cooperative motion planner continuously updates the robot’s trajectories to achieve the inferred tasks by repeatedly solving optimal control problems. The planner is designed to respond interactively to changes in the indicated task, avoid collisions in cluttered environments, handle time-varying objective functions, and achieve high-quality motions using a hybrid of numerical and sampling-based techniques. The system is applied to the problem of controlling a 6D robot manipulator using 2D mouse input in the context of two tasks: static target reaching and dynamic trajectory tracking. Simulations suggest that it enables the robot to reach intended targets faster and to track intended trajectories more closely than comparable techniques.     

Interleaving Planning and Robot Execution for Asynchronous User Requests

ROGUE is an architecture built on a real robot which provides algorithms for the integration of high-level planning, low-level robotic execution, and learning. ROGUE addresses successfully several of the challenges of a dynamic office gopher environment. This article presents the techniques for the integration of planning and execution.ROGUE uses and extends a classical planning algorithm to create plans for multiple interacting goals introduced by asynchronous user requests. ROGUE translates the planner';s actions to robot execution actions and monitors real world execution. ROGUE is currently implemented using the PRODIGY4.0 planner and the Xavier robot. This article describes how plans are created for multiple asynchronous goals, and how task priority and compatibility information are used to achieve appropriate efficient execution. We describe how ROGUE communicates with the planner and the robot to interleave planning with execution so that the planner can replan for failed actions, identify the actual outcome of an action with multiple possible outcomes, and take opportunities from changes in the environment.ROGUE represents a successful integration of a classical artificial intelligence planner with a real mobile robot.     

Path planning in GPS-denied environments via collective intelligence of distributed sensor networks

This paper proposes a framework for reactive goal-directed navigation without global positioning facilities in unknown dynamic environments. A mobile sensor network is used for localising regions of interest for path planning of an autonomous mobile robot. The underlying theory is an extension of a generalised gossip algorithm that has been recently developed in a language-measure-theoretic setting. The algorithm has been used to propagate local decisions of target detection over a mobile sensor network and thus, it generates a belief map for the detected target over the network. In this setting, an autonomous mobile robot may communicate only with a few mobile sensing nodes in its own neighbourhood and localise itself relative to the communicating nodes with bounded uncertainties. The robot makes use of the knowledge based on the belief of the mobile sensors to generate a sequence of way-points, leading to a possible goal. The estimated way-points are used by a sampling-based motion planning algorithm to generate feasible trajectories for the robot. The proposed concept has been validated by numerical simulation on a mobile sensor network test-bed and a Dubin’s car-like robot.     

<Emphasis Type="Italic">κ</Emphasis>-<Emphasis Type="Italic">PMP</Emphasis>: Enhancing Physics-based Motion Planners with Knowledge-Based Reasoning

Physics-based motion planning is a challenging task, since it requires the computation of the robot motions while allowing possible interactions with (some of) the obstacles in the environment. Kinodynamic motion planners equipped with a dynamic engine acting as state propagator are usually used for that purpose. The difficulties arise in the setting of the adequate forces for the interactions and because these interactions may change the pose of the manipulatable obstacles, thus either facilitating or preventing the finding of a solution path. The use of knowledge can alleviate the stated difficulties. This paper proposes the use of an enhanced state propagator composed of a dynamic engine and a low-level geometric reasoning process that is used to determine how to interact with the objects, i.e. from where and with which forces. The proposal, called κ-PMP can be used with any kinodynamic planner, thus giving rise to e.g. κ-RRT. The approach also includes a preprocessing step that infers from a semantic abstract knowledge described in terms of an ontology the manipulation knowledge required by the reasoning process. The proposed approach has been validated with several examples involving an holonomic mobile robot, a robot with differential constraints and a serial manipulator, and benchmarked using several state-of-the art kinodynamic planners. The results showed a significant difference in the power consumption with respect to simple physics-based planning, an improvement in the success rate and in the quality of the solution paths.     

A layered goal-oriented fuzzy motion planning strategy for mobile robot navigation.

Most conventional motion planning algorithms that are based on the model of the environment cannot perform well when dealing with the navigation problem for real-world mobile robots where the environment is unknown and can change dynamically. In this paper, a layered goal-oriented motion planning strategy using fuzzy logic is developed for a mobile robot navigating in an unknown environment. The information about the global goal and the long-range sensory data are used by the first layer of the planner to produce an intermediate goal, referred to as the way-point, that gives a favorable direction in terms of seeking the goal within the detected area. The second layer of the planner takes this way-point as a subgoal and, using short-range sensory data, guides the robot to reach the subgoal while avoiding collisions. The resulting path, connecting an initial point to a goal position, is similar to the path produced by the visibility graph motion planning method, but in this approach there is no assumption about the environment. Due to its simplicity and capability for real-time implementation, fuzzy logic has been used for the proposed motion planning strategy. The resulting navigation system is implemented on a real mobile robot, Koala, and tested in various environments. Experimental results are presented which demonstrate the effectiveness of the proposed fuzzy navigation system.     

A neural framework for adaptive robot control

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.     

Mobile robot path planning for fine-grained and smooth path spcification

This article introduces and draws a comparison on B-splines and clothoids for generating fine-grained, smooth path specifications as applied to mobile robot path planning. At one level, a sequence of objective points that the robot must attain to avoid obstacles and to progress toward its goal are supplied by a coarse path planner. Using B-spline and clothoid curves, these objective points are converted into a path of finer detail, as requisite to a robot driving controller/tracker. Through experimental results with the Navlabll, a mobile robot vehicle at Carnegie Mellon University (CMU), we differentiate the advantages of this approach over conventional poly-line fit/round corner used to date. © 2995 John Wiley & Sons, Inc.     

Mita Laboratory,Electric Engineering Section,Faculty of Engineering,The Chiba University

This paper describes a local path planning method for a mobile robot to search for a path in an unknown environment by using visual information. The mobile robot system has a hierarchical path planning system which searches for a path efficiently in an uncertain environment. The planning system consists of a global planner and a local planner. The global planner gives a global path in terms of a sequence of visual sub-goals. Then the local planner generates a local path between the sub-goals with the help of a visual sensor. The main focus of this paper is on local path planning, which provides real-time guidance to the system. A visual sensor can provide useful information about the environment. So, an algorithm is proposed to generate avoiding points by using visual information to bypass unknown obstacles in the local path planning. Local path planning in a simple environment is simulated by using three-dimensional graphics. A simple experiment is also done for the case where there are two obstacles. The validity of the proposed method is verified by these simulations and experimental results.     

Roadmap Coverage Improvement Using a Node Rearrangement Method for Mobile Robot Path Planning

Abstract

This paper proposes a method to efficiently abstract the traversable regions of a bounded two-dimensional environment using the probabilistic roadmap (PRM) to plan the path for a mobile robot. The proposed method uses centroidal Voronoi tessellation to autonomously rearrange the positions of initially randomly generated nodes. The PRM using the rearranged nodes covers most of the traversable regions in the environment and regularly divides them. The rearranged roadmap reduces the search space of a graph search algorithm and helps to promptly answer arbitrary queries in the environment. The mobile robot path planner using the proposed rearranged roadmap was integrated with a local planner that considers the kinematic properties of a mobile robot, and the efficiency and the safety of the paths were verified by simulation.     

Integrating planning and control for single-bodied wheeled mobile robots

This paper presents an approach to couple path planning and control for mobile robot navigation in a hybrid control framework. We build upon an existing hybrid control approach called sequential composition, in which a set of feedback control policies are prescribed on well-defined domains contained in the robot’s free space. Each control policy drives the robot to a goal set, which lies in the domain of a subsequent policy. Control policies are deployed into the free state space so that when composed among one another, the overall action of the set of control policies drives the robot to perform a task, such as moving from a start to a goal location or patrolling a perimeter. A planner determines the sequence of control policies to be invoked. When control policies defined in this framework respect the low-level dynamics and kinematics of the system, this formal approach guarantees that high-level tasks are either accomplished by a given set of policies, or verifies that the tasks are not achievable with the given policies.     

Towards modelling complex robot training tasks through system identification

Previous research has shown that sensor–motor tasks in mobile robotics applications can be modelled automatically, using NARMAX system identification, where the sensory perception of the robot is mapped to the desired motor commands using non-linear polynomial functions, resulting in a tight coupling between sensing and acting — the robot responds directly to the sensor stimuli without having internal states or memory.However, competences such as for instance sequences of actions, where actions depend on each other, require memory and thus a representation of state. In these cases a simple direct link between sensory perception and the motor commands may not be enough to accomplish the desired tasks. The contribution of this paper to knowledge is to show how fundamental, simple NARMAX models of behaviour can be used in a bootstrapping process to generate complex behaviours that were so far beyond reach.We argue that as the complexity of the task increases, it is important to estimate the current state of the robot and integrate this information into the system identification process. To achieve this we propose a novel method which relates distinctive locations in the environment to the state of the robot, using an unsupervised clustering algorithm. Once we estimate the current state of the robot accurately, we combine the state information with the perception of the robot through a bootstrapping method to generate more complex robot tasks: We obtain a polynomial model which models the complex task as a function of predefined low level sensor–motor controllers and raw sensory data.The proposed method has been used to teach Scitos G5 mobile robots a number of complex tasks, such as advanced obstacle avoidance, or complex route learning.     

AI Planner Assisted Test Generation

This paper describes an AI planner assisted approach to generate test cases for system testing based on high level test objectives. We use four levels of test generation: the metaprocessor, the preprocessor, the AI planner, and the postprocessor levels. Test generation is based on an extended UML model of the system under test and a mapping of high-level test objectives into initial and goal conditions of the planner. Test objectives are derived from a series of interviews with professional testers. We suggest various options for test criteria related to test objectives. The AI planner was used to generate hundreds of test cases for a robot controlled tape silo. The planner generated tests within a reasonable time. It was successful for each test objective given.     

Acquiring Mobile Robot Behaviors by Learning Trajectory Velocities

The development of robots that learn from experience is a relentless challenge confronting artificial intelligence today. This paper describes a robot learning method which enables a mobile robot to simultaneously acquire the ability to avoid objects, follow walls, seek goals and control its velocity as a result of interacting with the environment without human assistance. The robot acquires these behaviors by learning how fast it should move along predefined trajectories with respect to the current state of the input vector. This enables the robot to perform object avoidance, wall following and goal seeking behaviors by choosing to follow fast trajectories near: the forward direction, the closest object or the goal location respectively. Learning trajectory velocities can be done relatively quickly because the required knowledge can be obtained from the robot's interactions with the environment without incurring the credit assignment problem. We provide experimental results to verify our robot learning method by using a mobile robot to simultaneously acquire all three behaviors.     

Planning procedural advice

A planner which generates advice about the procedures which should be carried out by a human agent in order to achieve a goal is described. The fact that the agent is a person, not a robot, makes it possible to develop plans cooperatively with the user in the course of a dialogue, but imposes special requirements on the planner. The planner should be capable of taking advantage of the user's knowledge and abilities; of providing partial plans; of planning even in the absence of complete knowledge about the user's current state; of re-planning when the execution does not succeed or the situation changes; and of providing explanations of its advice. The paper considers the implications of these requirements on the design of such an advisory planner, implemented as part of the ‘Advice System’, a knowledge-based system for advising members of the public about welfare benefits.     

Tangential Gap Flow (TGF) navigation: A new reactive obstacle avoidance approach for highly cluttered environments

This paper presents a novel reactive collision avoidance method for mobile robots moving in dense and cluttered environments. The proposed method, entitled Tangential Gap flow (TGF), simplifies the navigation problem using a divide and conquer strategy inspired by the well-known Nearness-Diagram Navigation (ND) techniques. At each control cycle, the TGF extracts free openings surrounding the robot and identifies the suitable heading which makes the best progress towards the goal. This heading is then adjusted to avoid the risk of collision with nearby obstacles based on two concepts namely, tangential and gap flow navigation. The tangential navigation steers the robot parallel to the boundary of the closest obstacle while still emphasizing the progress towards the goal. The gap flow navigation safely and smoothly drives the robot towards the free area in between obstacles that lead to the target. The resultant trajectory is faster, shorter and less-oscillatory when compared to the ND methods. Furthermore, identifying the avoidance maneuver is extended to consider all nearby obstacle points and generate an avoidance rule applicable for all obstacle configurations. Consequently, a smoother yet much more stable behavior is achieved. The stability of the motion controller, that guides the robot towards the desired goal, is proved in the Lyapunov sense. Experimental results including a performance evaluation in very dense and complex environments demonstrate the power of the proposed approach. Additionally, a discussion and comparison with existing Nearness-Diagram Navigation variants is presented.