Organizational Unit:

Humanoid Robotics Laboratory

Permanent Link

https://hdl.handle.net/1853/70718

Parent Organization

Organizational Unit

Institute for Robotics and Intelligent Machines (IRIM)

Full item page

Publication Search Results

Now showing 1 - 9 of 9

Linguistic Transfer of Human Assembly Tasks to Robots

(Georgia Institute of Technology, 2012-10) Dantam, Neil ; Essa, Irfan ; Stilman, Mike

We demonstrate the automatic transfer of an assembly task from human to robot. This work extends efforts showing the utility of linguistic models in verifiable robot control policies by now performing real visual analysis of human demonstrations to automatically extract a policy for the task. This method tokenizes each human demonstration into a sequence of object connection symbols, then transforms the set of sequences from all demonstrations into an automaton, which represents the task-language for assembling a desired object. Finally, we combine this assembly automaton with a kinematic model of a robot arm to reproduce the demonstrated task.
Diverse Workspace Path Planning for Robot Manipulators

(Georgia Institute of Technology, 2012-07) Quispe, Ana Huamán ; Stilman, Mike

We present a novel algorithm that generates a set of diverse workspace paths for manipulators. By considering more than one possible path we give our manipulator the flexibility to choose from many possible ways to execute a task. This is particularly important in cases in which the best workspace path cannot be executed by the manipulator (e.g. due to the presence of obstacles that collide with the manipulator links). Our workspace paths are generated such that a distance metric between them is maximized, allowing them to span different workspace regions. Manipulator planners mostly focus on solving the problem by analyzing the configuration space (e.g. Jacobian-based methods); our approach focuses on analyzing alternative workspace paths which are comparable to the optimal solution in terms of length. This paper introduces our intuitive algorithm and also presents the results of a series of experiments performed with a simulated 7 DOF robotic arm.
Detecting Partially Occluded Objects via Segmentation and Validation

(Georgia Institute of Technology, 2012) Levihn, Martin ; Dutton, Matthew ; Trevor, Alexander J. B. ; Stilman, Mike

This paper presents a novel algorithm: Verfied Partial Object Detector (VPOD) for accurate detection of partially occluded objects such as furniture in 3D point clouds. VPOD is implemented and validated on real sensor data obtained by our robot. It extends Viewpoint Feature Histograms (VFH) which classify unoccluded objects to also classifying partially occluded objects such as furniture that might be seen in typical office environments. To achieve this result, VPOD employs two strategies. First, object models are segmented and the object database is extended to include partial models. Second, once a matching partial object is detected, the full object model is aligned back into the scene and verified for consistency with the point cloud data. Overall, our approach increases the number of objects found and substantially reduces false positives due to the verification process.
Algorithms for Linguistic Robot Policy Inference from Demonstration of Assembly Tasks

(Georgia Institute of Technology, 2012) Dantam, Neil ; Essa, Irfan ; Stilman, Mike

We describe several algorithms used for the inference of linguistic robot policies from human demonstration. First, tracking and match objects using the Hungarian Algorithm. Then, we convert Regular Expressions to Nondeterministic Finite Automata (NFA) using the McNaughton-Yamada-Thompson Algorithm. Next, we use Subset Construction to convert to a Deterministic Finite Automaton. Finally, we minimize finite automata using either Hopcroft's Algorithm or Brzozowski's Algorithm.
Ach: IPC for Real-Time Robot Control

(Georgia Institute of Technology, 2011) Dantam, Neil ; Stilman, Mike

We present a new Inter-Process Communication (IPC) mechanism and library. Ach is uniquely suited for coordinating perception, control drivers, and algorithms in real-time systems that sample data from physical processes. Ach eliminates the Head-of-Line Blocking problem for applications that always require access to the newest message. Ach is efficient, robust, and formally verified. It has been tested and demonstrated on a variety of physical robotic systems. Finally, the source code for Ach is available under an Open Source BSD-style license.
Time-Optimal Path Following with Bounded Joint Accelerations and Velocities

(Georgia Institute of Technology, 2011) Kunz, Tobias ; Stilman, Mike

This paper presents a method to generate the time-optimal trajectroy that exactly follows a given differentiable joint-space path within given bounds on joint accelerations and velocities. We also present a path preprocessing method to make nondifferentiable paths differentiable by adding circular blends.
Design and Development of a Dynamically-Balancing Holonomic Robot

(Georgia Institute of Technology, 2011) Reynolds-Haertle, Saul ; Stilman, Mike

This paper describes the design, control, and construction of Golem Wing, the first vehicle which both balances dynamically and has entirely holonomic ground movement. A nonstandard linear arrangement of mecanum wheels gives it the load-lifting, performance, and manipulation benefits of a dynamically-balancing platform without the maneuvering difficulties exhibited by previous balancing platforms. We show that the arrangement is capable of holonomic motion, describe a controller that maintains dynamic balance during holonomic motion, and show an implementation of the system in hardware that validate our assertions.
Turning Paths Into Trajectories Using Parabolic Blends

(Georgia Institute of Technology, 2011) Kunz, Tobias ; Stilman, Mike

We present an approach for converting a path of multiple continuous linear segments into a trajectory that satisfies velocity and acceleration constraints and closely follows the given path without coming to a complete stop at every waypoint. Our method applies parabolic blends around waypoints to improve speed. In contrast to established methods that smooth trajectories with parabolic blends, our method does not require the timing of waypoints or durations of blend phases. This makes our approach particularly useful for robots that must follow kinematic paths that are not explicitly parametrized by time. Our method chooses timing automatically to achieve high performance while satisfying the velocity and acceleration constraints of a given robot.
Efficient Opening Detection

(Georgia Institute of Technology, 2011) Levihn, Martin ; Stilman, Mike

We present an efficient and powerful algorithm for detecting openings. Openings indicate the existence of a new path for the robot. The reliable detection of new openings is especially relevant to the domain of Navigation Among Movable Obstacles in known [7] as well as unknown [2] environments. Tremendous speed-ups for algorithms in these domains can be achieved by limiting the considerations of obstacle manipulations to cases where manipulations create new openings. The presented algorithm can detect openings for obstacles of arbitrary shapes being displaced in arbitrary directions in changing environments. To the knowledge of the authors, this is the first algorithm to achieve efficient opening detection for arbitrary shaped obstacles.