The objective of the thesis is to compare and study recent visual grasping techniques which areapplied on a robotic arm for grasping of unknown objects in an indoor environment.The novelty of the thesis is that the study has led to questioning the general approach used byresearchers to solve the grasping problem. The result can help future researchers in investing more onthe problem areas of grasping techniques and can also lead us to question ourselves on the approachwe are using to solve the grasping problem.

Humans often learn to manipulate objects by observing other people. In much the same way, robots can use imitation learning to pick up useful skills. A system is detailed here for using imitation learning to teach a robot to grasp objects using both hand and whole-body grasps, which use the arms and torso as well as hands. Demonstration grasp trajectories are created by teleoperating a simulated robot to pick up simulated objects. When presented with a new object, the system compares it against the objects in a stored database to pick a demonstrated grasp used on a similar object. Both objects are modeled as a combination of primitives—boxes, cylinders, and spheres—and by considering the new object to be a transformed version of the demonstration object, contact points are mapped from one object to the other. The best kinematically feasible grasp candidate is chosen with the aid of a grasp quality metric. To test the success of the chosen grasp, a full, collision-free grasp trajectory is found and an attempt is made to execute in the simulation. The implemented system successfully picks up 92 out of 100 randomly generated test objects in simulation. / Singapore-MIT Alliance (SMA)

Posterior Cortical Atrophy (PCA) is a rare clinical syndrome characterised by the predominance of higher-order visual disturbances. Deficits result from a progressive neurodegeneration of occipito-temporal and occipito-parietal cortices. Due to its relative scarcity, many common symptoms of PCA, such as visuomotor dysfunction, have yet to be fully investigated. The current study sought to explore the visuomotor abilities of four individuals with PCA by testing their ability to reach out and grasp real objects under various viewing conditions. The patients demonstrated many of the same deficits as those seen in individuals with optic ataxia, including impaired grip scaling to peripheral targets, poor selection of stable grasp sites, and evidence of ‘magnetic misreaching’ – a pathological reaching bias towards the point of visual fixation. Unlike individuals with pure optic ataxia, however, the patients in the current study showed symptoms indicative of damage to the ventral stream of visual processing, including abolished grip scaling during memory-guided grasping and an inability to differentiate objects based on their shape. This research increases our understanding of the visuomotor deficits associated with PCA. It also adds to our knowledge of how visual information is processed in the brain, including the complex interaction between vision for action and vision for perception.

Posterior Cortical Atrophy (PCA) is a rare clinical syndrome characterised by the predominance of higher-order visual disturbances. Deficits result from a progressive neurodegeneration of occipito-temporal and occipito-parietal cortices. Due to its relative scarcity, many common symptoms of PCA, such as visuomotor dysfunction, have yet to be fully investigated. The current study sought to explore the visuomotor abilities of four individuals with PCA by testing their ability to reach out and grasp real objects under various viewing conditions. The patients demonstrated many of the same deficits as those seen in individuals with optic ataxia, including impaired grip scaling to peripheral targets, poor selection of stable grasp sites, and evidence of ‘magnetic misreaching’ – a pathological reaching bias towards the point of visual fixation. Unlike individuals with pure optic ataxia, however, the patients in the current study showed symptoms indicative of damage to the ventral stream of visual processing, including abolished grip scaling during memory-guided grasping and an inability to differentiate objects based on their shape. This research increases our understanding of the visuomotor deficits associated with PCA. It also adds to our knowledge of how visual information is processed in the brain, including the complex interaction between vision for action and vision for perception.

Grasping is fundamentally important for our successful interaction with the environment. Grasping with both hands is phylogenetically older than the hand yet its underlying mechanisms are poorly understood. The objective of this research is to examine bimanual grasping and its underlying mechanisms. Two experiments were conducted to examine whether bimanual grasping involves both hemispheres equally or only one dominant hemisphere, and to examine whether information crosses at an early visual level and/or at later sensorimotor/motor levels. The first experiment examined participants’ grasping and reaching movements while they fixated either to the left or right of the object. For the second experiment, EEG data was recorded while participants performed a similar task. The results from both experiments suggested that when we grasp an object with both hands, the left and right hemispheres control the action equally, and visual information is shared before it reaches areas that are involved in motor control.

Grasping is fundamentally important for our successful interaction with the environment. Grasping with both hands is phylogenetically older than the hand yet its underlying mechanisms are poorly understood. The objective of this research is to examine bimanual grasping and its underlying mechanisms. Two experiments were conducted to examine whether bimanual grasping involves both hemispheres equally or only one dominant hemisphere, and to examine whether information crosses at an early visual level and/or at later sensorimotor/motor levels. The first experiment examined participants’ grasping and reaching movements while they fixated either to the left or right of the object. For the second experiment, EEG data was recorded while participants performed a similar task. The results from both experiments suggested that when we grasp an object with both hands, the left and right hemispheres control the action equally, and visual information is shared before it reaches areas that are involved in motor control.

Grasping is a useful ability that allows manipulators to restrain objects to a desired location or trajectory. Whole arm grasps are grasps that use the entire surface of the manipulator to apply contacts to an object. The problem of determining the shape of an object and planning a grasp for that object with a snake-like robot are considered in this work. Existing algorithms that attempt to allow robots to plan and perform whole arm grasps are lacking, they either use restrictive assumptions or have unrealistic demands in terms of required hardware. The work presented here allows even the most basic of robots to plan grasps on unknown objects whilst using a minimum of assumptions.The new developed Octograsp algorithm is a method of gaining information regarding the shape of the object to be grasped through tactile information alone. This contact information is processed using an inverse convex hull algorithm to build a model of the object's shape and position. The performance of the algorithms are examined using both simulations and experimental hardware, it is shown that accuracy errors as low as 3.1% can be obtained. The accuracy of the model depends upon factors such as the complexity of the object and the suitability of the robot. Manipulators consisting of a large number of small links with relaxed rotational constraints outperform other configurations. It is also shown that the accuracy can be improved by between 11% and 17% by contacting the object from multiple orientations, whilst also encircling from multiple positions can provide a very large improvement of between 56% to 86%. These methods allow even the coarse contact information provided by the experimental equipment to attain a model with an accuracy error of only 26%.A second novel algorithm is described that uses the information provided from the first algorithm to plan strong grasps over the desired object. The algorithm takes, on average, 25.1 seconds to plan the grasp. The mean strength of the planned grasps is 0.3816 using the wrench ball measure, this is firmly in the very good region. Several robotic configurations, as well as objects, are used to test the performance of the algorithm. The optimal parameters of the algorithm are investigated by using the results of 51030 different tests. It is again shown that robots that consist of a large number of small links and with high rotational ability perform the best.

In this thesis, we introduce our lasso-type grasping scheme. This 3-D lasso-type grasping scheme, different from the previously performed grasping schemes which are either planar or fixed base, is the novelty of our approach where the snake robot grasps an object with any of its body links which are at close proximity to the object while undergoing its serpentine motion with the remaining links and dragging the grasped object. Since our snake robot has the pitch motion for every link, we can ensure that the links do not run into each other as they wrap around the object. A lasso-type power grasp is then possible for our 15-link snake robot as seen in the simulation results of this thesis. Furthermore we develop the kinematic and control models for lasso-type grasping and for dragging the grasped object to a desired state. This control model includes an adaptively changing feedback gain which prevents excessively large inputs to corrupt the serpentine locomotion control. According to our lasso-type grasping model, while the snake robot can grasp the object beginning with the any body link at close proximity of the object, the contact points can be controlled to generate the curvilinear grasping curve by using our lasso-type grasping procedure. For dragging the grasped object, we define a scheme which can determine the appropriate desired state to drag the grasped object to a desired position. The stability of the grasped object is important to resist the disturbance forces as well as the force closure grasping is important to counteract the disturbance force. To analyze the stability of the lasso-type grasping, we introduce a stability model of lasso-type grasping based on contact stiffness matrices that faces the snake to regrasp when gone unstable.

This paper deals with the class of problems that involve finding where to place or how to move a solid object in the presence of obstacles. The solution to this class of problems is essential to the automatic planning of manipulator transfer movements, i.e. the motions to grasp a part and place it at some destination. This paper presents algorithms for planning manipulator paths that avoid collisions with objects in the workspace and for choosing safe grasp points on objects. These algorithms allow planning transfer movements for Cartesian manipulators. The approach is based on a method of computing an explicit representation of the manipulator configurations that would bring about a collision.

Grasping and manipulation of objects is an integral part of a robot’s physical interaction with the environment. In order to cope with real-world situations, sensor based grasping of objects and grasp stability estimation is an important skill. This thesis addresses the problem of predicting the stability of a grasp from the perceptions available to a robot once fingers close around the object before attempting to lift it. A regrasping step can be triggered if an unstable grasp is identified. The percepts considered consist of object features (visual), gripper configurations (proprioceptive) and tactile imprints (haptic) when fingers contact the object. This thesis studies tactile based stability estimation by applying machine learning methods such as Hidden Markov Models. An approach to integrate visual and tactile feedback is also introduced to further improve the predictions of grasp stability, using Kernel Logistic Regression models. Like humans, robots are expected to grasp and manipulate objects in a goal-oriented manner. In other words, objects should be grasped so to afford subsequent actions: if I am to hammer a nail, the hammer should be grasped so to afford hammering. Most of the work on grasping commonly addresses only the problem of finding a stable grasp without considering the task/action a robot is supposed to fulfill with an object. This thesis also studies grasp stability assessment in a task-oriented way based on a generative approach using probabilistic graphical models, Bayesian Networks. We integrate high-level task information introduced by a teacher in a supervised setting with low-level stability requirements acquired through a robot’s exploration. The graphical model is used to encode probabilistic relationships between tasks and sensory data (visual, tactile and proprioceptive). The generative modeling approach enables inference of appropriate grasping configurations, as well as prediction of grasp stability. Overall, results indicate that the idea of exploiting learning approaches for grasp stability assessment is applicable in realistic scenarios. / <p>QC 20121026</p>