Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 20 for “"Non-prehensile."”.
-
Non-Prehensile Mobile Agent Interactive Navigation in Cluttered Environments
… for completing tasks. This thesis studies non-prehensile interactive navigation (NPIN), where robots interact with their surroundings using non-grasping, contact-based actions. These interactions present significant challenges, including complex interaction dynamics, long-horizon planning …
-
Physics-Based Multi-Object Tracking for Non-Prehensile Robotic Manipulation
This thesis presents an algorithm to track objects, particularly designed to address the challenge of “tracking objects in cluttered environments.” The key point is that the robot can continuously track the target objects, even when they are heavily occluded. This method can be used to retrieve an …
-
Dynamic Admittance Parameterization for Non-Prehensile Multi-Robot Transport with Optimal Coordinated Planning
The Dynamic Admittance Parameterization of Non-Prehensile Multi-Robot Trans- port with Optimal Coordinated Planning (DYNAMO) architecture offers a practical framework for cooperative payload transportation using two robots equipped with nonholonomic mobile bases and four-degree-of-freedom …
-
Real-time predictions from unlabeled high-dimensional sensory data during non-prehensile manipulation
… from unlabeled streams of sensory data for a non-prehensile manipulation task. Specifically, we address the problem of making real-time predictions of the mass, friction coefficient, and compliance of a block during a topple-slide task, using an unlabeled mix of 1650 features composed of pose, …
-
Human-In-The-Loop Planning and Control for Non-Prehensile Manipulation in Clutter
… to retrieve a goal object. The robot considers non-prehensile manipulation and is, therefore, required to interact with objects and push them out of the way to create space. Reaching Through Clutter is in the NP-Hard class and is, therefore, a computationally challenging problem. This is due to …
-
Exploring structured predictions from sensorimotor data during non-prehensile manipulation using both simulations and robots
… robotic system. The framework is evaluated for a non-prehensile ”topple-and-slide” task, where the data from a set of sensorimotor streams are used to predict the task property, such as object mass, friction coefficient, and compliance of the block being manipulated. Given the collected data …
-
Sacral Morphology of Prehensile-Tailed Primates in Relation to Biomechanical Loading
The few available comparative studies of prehensile tail anatomy in primates have established that several features of the caudal vertebrae are associated with adaptation to the increased loading of the tail during prehension. Given that the caudal vertebrae are anchored to the sacrum, it stands to …
-
Prezygapophyseal articular surface morphology in the galagid tail : the influence of tail use and vertebral level
… majority of tail anatomy studies have focused on prehensile tails, with all other forms of tail use lumped into 'non-prehensile'. This distinction conceals the diversity of tail use in the 'non-prehensile' category. For example, vertical clinging and leaping primates use their tails to …
-
Robust Planning and Coordination under Uncertainty for Aerial Manipulation and Multi-Robot Teams
… with unknown mass. I then explore high-precision prehensile aerial manipulation in the form of pick-and-place experiments with visual object pose estimation, visual odometry, and motion planning computed onboard a small form factor vehicle. For non-prehensile aerial manipulation, I introduce a …
-
Generative and predictive models for robust manipulation
… and derived from learnt physical models in non-prehensile tasks such as pushing. Manipulation skills can be made robust in different ways: first by improving time performance for grasp synthesis, second by employing active perceptual strategies that exploit generated grasp action hypothesis …
-
Model Predictive Control with Efficient Trajectory Optimisation for Contact-based Manipulation
… efficiently manipulate their environments using non-prehensile manipulation. However, enabling robots to make use of these efficient non-prehensile manipulation actions is challenging, particularly when tasking robots to manipulate cluttered environments. There are a variety of issues that need …
-
HIERARCHICAL LEARNING FOR WHOLE-BODY LOCO-MANIPULATION IN MULTI-LEGGED ROBOTS
… to their own bodies. Pushing offers an efficient non-prehensile manipulation strategy by avoiding complex grasping while enabling direct regulation of object motion. However, pushing heavy or irregular objects requires both strong manipulation capability and stable whole-body coordination. To …
-
PLANNING TOWARDS EFFECTIVE MOBILE ROBOT NAVIGATION IN UNSTRUCTURED ENVIRONMENTS
… learning-based approach for collision-aware, non-prehensile, planar pushing manipulation of box-shaped objects, using target-driven end-to-end model.
-
Robotic manipulation by pushing at a single point with constant velocity : modeling and techniques
… without grasping the object being manipulated. Non-prehensile manipulation allows a robot to interact in situations which would otherwise be impossible due to object size or mass. This thesis investigates the most general pushing mode, that of a single contact point, formed either as a fixed …
-
Physical Setup and Experiments to Test Multi-Wheeled-Robot Operations in Search and Collaborative Transport Applications
… The first part centres on collaborative non-prehensile transport using R2P2 (Roles with Rules and Proportional-control Primitive), a decentralized framework in which each robot selects a Push, Prevent, or Support role based solely on its relative position and the object's pose. This …
-
Home-based Egocentric Video Systems to Characterize Hand Grasps in Individuals with Cervical Spinal Cord Injury
… grasps into power, precision, intermediate, and non-prehensile categories. 4. Finally, in the fourth study, we employed a semantic clustering approach to summarize hand grasps without restriction to predefined grasp types. The studies in this thesis demonstrate for the first time automated …
-
Learning deep policies for physics-based robotic manipulation in cluttered real-world environments
… heuristic. VisualRHP generates, in closed-loop, prehensile and non-prehensile manipulation actions to manipulate a desired object in clutter while avoiding dropping obstacle objects off the edge of the manipulation surface. To acquire the heuristic of VisualRHP, we develop deep imitation learning …
-
Controlling Contact Transitions for Dynamic Robots
… dexterous dynamic manipulation through complex non-prehensile tasks that require considering the full spectrum of hybrid contact modes. We leverage recent advancements in contact-implicit MPC to generate contact-rich motion plans in real-time. We demonstrate, through careful integration of the …
-
Evaluation of periodontal scaling task and development of force-endurance models for simulated scaling task
… the force balance and endurance issues for non-prehensile movements of hand. However, little information is available on the force exerted in precision gripping employed in health care. Professionals, especially dental hygienists, when treating patients adopt awkward postures for extended …
-
Tactile Perception And Visuotactile Integration For Robotic Exploration
… feature descriptor for object recognition using non-prehensile tactile probing alone. Then, we investigate in making the tactile modality, local and slow by nature, more efficient for the task by predicting the most cost-effective moves using active exploration. To combine the local and physical …