A5027878263- Robotic Path Planning Algorithms
- Robot Manipulation and Learning
- Robotic Mechanisms and Dynamics
- Robotic Locomotion and Control
- Robotics and Sensor-Based Localization
- Soft Robotics and Applications
- Teleoperation and Haptic Systems
- Modular Robots and Swarm Intelligence
- Prosthetics and Rehabilitation Robotics
- Human Motion and Animation
- Tactile and Sensory Interactions
- Advanced Manufacturing and Logistics Optimization
- Virtual Reality Applications and Impacts
- Optical Coherence Tomography Applications
- Advanced Control Systems Optimization
- Reinforcement Learning in Robotics
- Corneal surgery and disorders
- Advanced Vision and Imaging
- Retinal and Macular Surgery
- Autonomous Vehicle Technology and Safety
- Surgical Simulation and Training
- Guidance and Control Systems
- Optimization and Search Problems
- Intraocular Surgery and Lenses
- Manufacturing Process and Optimization
University of Illinois Urbana-Champaign
2018-2025
Duke University
2014-2021
Harvey Mudd College
2021
University of Freiburg
2019
Duke Medical Center
2018
Electronic Concepts and Engineering (United States)
2017
Indiana University Bloomington
2009-2016
Indiana University
2010-2014
Indiana University – Purdue University Indianapolis
2011
Stanford University
2006-2010
This paper presents an overview of the inaugural Amazon Picking Challenge along with a summary survey conducted among 26 participating teams. The challenge goal was to design autonomous robot pick items from warehouse shelf. task is currently performed by human workers, and there hope that robots can someday help increase efficiency throughput while lowering cost. We report on 28-question posed teams learn about each team's background, mechanism design, perception apparatus, planning,...
In this paper we study the quasi-static motion of large legged robots that have many degrees freedom. While gaited walking may suffice on easy ground, rough and steep terrain requires unique sequences footsteps postural adjustments specifically adapted to terrain's local geometric physical properties. present a planner computes these motions by combining graph searching generate sequence candidate footfalls with probabilistic sample-based planning continuous reach footfalls. To improve...
Asymptotically-optimal sampling-based motion planners, like RRT*, perform vast amounts of collision checking, and are hence rather slow to converge in complex problems where checking is relatively expensive. This paper presents two novel Lazy-PRM* Lazy-RRG*, that eliminate the majority checks using a lazy strategy. They sampling-based, any-time, asymptotically complete algorithms grow network feasible vertices connected by edges. Edges not immediately checked for collision, but only when...
We present algorithms for simulating and visualizing the insertion steering of needles through deformable tissues surgical training planning. Needle is an essential component many clinical procedures such as biopsies, injections, neurosurgery, brachytherapy cancer treatment. The success these depends on accurate guidance needle tip to a target while avoiding vital tissues. deforms body tissues, making placement difficult. Our interactive simulator models coupling between steerable tissue....
Robots that perform complex manipulation tasks must be able to generate strategies make and break contact with the object. This requires reasoning in a motion space particular multi-modal structure, which state contains both discrete mode (the state) continuous configuration robot object poses). In this paper we address planning common setting where is high-dimensional, there are infinity of modes. We present highly general algorithm, Random-MMP, repeatedly attempts switches sampled at...
This paper formulates a new minimum constraint removal (MCR) motion planning problem in which the objective is to remove fewest geometric constraints necessary connect start and goal state with free path. It describes probabilistic roadmap planner for MCR continuous configuration spaces that operates by constructing increasingly refined roadmaps, efficiently solves discrete problems on these networks. A number of theoretical results are given MCR, including proof it NP-hard reduction from...
This paper presents a method for generating dynamically feasible, keyframe-interpolating motions robots undergoing contact, such as in legged locomotion and manipulation. The first stage generates twice-differentiable interpolating path that obeys kinematic contact constraints up to user-specified tolerance. second optimizes speeds along the minimize time while satisfying dynamic constraints. supports velocity, acceleration, torque constraints, polyhedral friction at an arbitrary number of...
Differential dynamic programming (DDP) is a widely used trajectory optimization technique that addresses nonlinear optimal control problems, and can readily handle cost functions. However, it does not either state or constraints. This paper presents novel formulation of DDP able to accommodate arbitrary inequality constraints on both control. The main insight in standard quadratic approximation the value function be derived using recursive backward pass, however formulae are only valid for...
Motion planning problems encountered in manipulation and legged locomotion have a distinctive multi-modal structure, where the space of feasible configurations consists intersecting submanifolds, often different dimensionalities. Such does not possess expansiveness, property that characterizes whether queries can be solved efficiently with traditional probabilistic roadmap (PRM) planners. In this paper we present new PRM-based algorithm for number manifolds is finite. We also analyze...
This paper presents a non-gaited motion planner for humanoid robots navigating very uneven and sloped terrain. The allows contact with any pre-designated part of the robot's body, since use hands or knees (in addition to feet) may be required balance. It uses probabilistic, sample-based approach compute each step. One challenge this is that most randomly sampled configurations do not satisfy all constraints (closed-chain, equilibrium, collision). To address problem, method iterative...
This paper considers a shortcutting heuristic to smooth jerky trajectories for many-DOF robot manipulators subject collision constraints, velocity bounds, and acceleration bounds. The repeatedly picks two points on the trajectory attempts replace intermediate with shorter, collision-free segment. Here, we construct segments that interpolate between endpoints specified in time-optimal fashion, while respecting These consist of parabolic straight-line curves, can be computed closed form....
During outbreaks of contagious diseases, healthcare workers are at high risk for infection due to routine interaction with patients, handling contaminated materials, and challenges associated safely removing protective gear. This poses an opportunity the use remote-controlled robots that could perform common nursing duties inside hazardous clinical areas, thereby minimizing exposure contagions other biohazards. paper describes development prototype system Tele-Robotic Intelligent Nursing...
This paper presents an equivalence between feasible kinodynamic planning and optimal planning, in that any problem can be transformed into a series of problems state-cost space, whose solutions approach the optimum. transformation yields meta-algorithm produces asymptotically planner, given planner as subroutine. The is proven to formula derived relating expected running time solution suboptimality. It directly applicable wide range because it does not resort use steering functions or...
Ophthalmic microsurgery is technically difficult because the scale of required surgical tool manipulations challenge limits surgeon's visual acuity, sensory perception, and physical dexterity. Intraoperative optical coherence tomography (OCT) imaging with micrometer-scale resolution increasingly being used to monitor provide enhanced real-time visualization ophthalmic maneuvers, but surgeons still face limitations when manipulating instruments inside eye. Autonomously controlled robots are...