Recent robotic manipulation competitions have highlighted that sophisticated robots still struggle to achieve fast and reliable perception of task-relevant objects in complex, realistic scenarios. To improve these systems' perceptive speed and robustness, we present SegICP, a novel integrated solution to object recognition and pose estimation. SegICP couples convolutional neural networks and multi-hypothesis point cloud registration to achieve both robust pixel-wise semantic segmentation as well as accurate and real-time 6-DOF pose estimation for relevant objects.Our architecture achieves 1 cm position error and < 5 • angle error in real time without an initial seed. We evaluate and benchmark SegICP against an annotated dataset generated by motion capture.
This paper presents a new method for injecting human inputs in mixed initiative interactions between humans and robots. The method is based on a model predictive control (MPC) formulation, which inevitably involves predicting the system (robot dynamics as well as human inputs) into the future. These predictions are complicated by the fact that the human is interacting with the robot, causing the prediction method itself to have an effect on future human inputs. We investigate and develop different prediction schemes, including fixed and variable horizon MPCs and human input estimators of different orders. Through a search-and-rescue-inspired human operator study, we arrive at the conclusion that the simplest prediction methods outperform the more complex ones, i.e., in this particular case, less is indeed more.Index Terms-human-robot interaction, model-predictive control, mixed initiative initeractions.
This paper presents a control theoretic formulation and optimal control solution for integrating human control inputs subject to linear state constraints. The formulation utilizes a receding horizon optimal controller to update the control effort given the most recent state and human control input information. The novel solution to the corresponding finite horizon optimal control problem with terminal constraint is derived using Hilbert space methods. The control laws are applied to two planar human-driven mass-cart pendula, where the task is to synchronize the pendula's oscillations.
FAA's NextGen program aims at increasing the capacity of the national airspace, while ensuring the safety of aircraft. This paper provides a distributed merging and spacing algorithm that maximizes the throughput at the terminal phase of flight using the information provided through the ADS-B framework. Using dual decomposition, aircraft negotiate with each other and reach an agreement on optimal merging times, with respect to an associated cost, that ensures proper inter-aircraft spacing. We provide a feasibility analysis that gives sufficient conditions to guarantee that proper spacing is achievable and derive maximum throughput controllers based on the air traffic characteristics of the merging flight paths.
In this paper, we present a control theoretic formulation for composing human control inputs with an automatic controller for shared control of a quadruped rescue robot. The formulation utilizes a model predictive controller to guide human controlled leg positions to satisfy state constraints that correspond to static stability for the robot. A hybrid control architecture that incorporates the model predictive controller is developed to implement a gait that guarantees stable foot-placements for the robot. The algorithm is applied to a simulation of a quadruped rescue robot with human input provided through haptic joysticks.
The NextGen program is the FAA's response to the ever increasing air traffic, that provides tools to increase the capacity of national airspace, while ensuring the safety of aircraft. In support of this vision, this paper provides a decentralized algorithm based on dual decomposition for safe merging and spacing of aircraft at the terminal phase of the flight. Aircraft negotiate optimal merging times that ensure safety, while penalizing deviations from the nominal path. We provide feasibility conditions for the safe merging of all incoming legs of flight and put the viability of the proposed algorithm to the test through simulations.
This paper considers the problem of coordinating multiple pendula attached to mobile bases. In particular, the pendula should move in such a way that their motion is synchronized, which calls for two problems to be solved simultaneously, namely a constrained optimal control problem for each pendulum, and a constrained agreement problem across the network of pendula. A novel way of manipulating the initial conditions in the consensus equation is presented that will solve the latter of these problems, and simulation results are presented that support the viability of the proposed approach.
In this paper, we will present a hardware testbed for multi-UAV systems that bridges the gap between algorithm design and field deployment. The testbed allows for UAV coordination algorithms, that have been shown to work in simulation, to be further tested in an environment where limited on-board computational resources, wireless communication constraints, environmental noise, and differences in the UAVs modeled versus actual dynamics come into effect. In particular, we will introduce an efficient assignment algorithm. This algorithm is used in a multi-UAV ground convoy protection scenario, where UAVs escort the ground convoy and are deployed to check potential threats along the way.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.