Use of robots is rising in process applications where robots need to interact with parts using tools. Representative examples can be cleaning, polishing, grinding, etc. These tasks can be non-repetitive in nature and the physics-based models of the task performances are unknown for new materials and tools. In order to reduce operation cost and time, the robot needs to identify and optimize the trajectory parameters. The trajectory parameters that influence the performance can be speed, force, torque, stiffness, etc. Building physics-based models may not be feasible for every new task, material, and tool profile as it will require conducting a large number of experiments. We have developed a method that identifies the right set of parameters to optimize the task objective and meet performance constraints. The algorithm makes decisions based on uncertainty in the surrogate model of the task performance. It intelligently samples the parameter space and selects a point for experimentation from the sampled set by determining its probability to be optimum among the set. The iterative process leads to rapid convergence to the optimal point with a small number of experiments. We benchmarked our method against other optimization methods on synthetic problems. The method has been validated by conducting physical experiments on a robotic cleaning problem. The algorithm is general enough to be applied to any optimization problem involving black box constraints.

This paper presents planning algorithms for robotic cleaning of stains on nonplanar surfaces. Access to different portions of the stain may require frequent repositioning and reorienting of the object. Some portions with prominent stain may require multiple passes to remove the stain completely. Two robotic arms have been used in the experiments. The object is immobilized with one arm and the cleaning tool is manipulated with the other. The algorithm generates a sequence of reorientation and repositioning moves required to clean the part after analyzing the stain. The plan is generated by accounting for the kinematic constraints of the robot. Our algorithm uses a depth-first branch-and-bound search to generate setup plans. Cleaning trajectories are generated and optimal cleaning parameters are selected by the algorithm. We have validated our approach through numerical simulations and robotic cleaning experiments with two KUKA robots.

Unmanned vehicles are emerging as an attractive tool for persistent monitoring tasks of a given area, but need automated planning capabilities for effective unattended deployment. Such an automated planner needs to generate collision-free coverage paths by steering waypoints to locations that both minimize the path length and maximize the amount of information gathered along the path. The approach presented in this paper significantly extends prior work and handles motion uncertainty of an unmanned vehicle and the presence of obstacles by using a Markov Decision Process based approach to generate collision-free paths. Simulation results show that the proposed approach is robust to significant motion uncertainties and reduces the probability of collision with obstacles in the environment.

This paper describes RoboTerp, a quadrupedal amphibious robot that achieves locomotion on land and in water with the same legs by switching gaits to match the terrain. The central idea hinges on a passive compliant mechanism attached to the lower leg that enables it to behave like a valve during movement in water. The direction of this valve-like mechanism is aligned such that rhythmic oscillations of the legs generate a net thrust that propels the robot forward in water. By design, this oscillatory leg movement achieves splash-free swimming, and thereby overcomes the shortcomings of most previous wheel-leg based designs, in which rotational movement causes water splashing that leads to significant turbulence in the robot surroundings. We examined different materials and morphological parameters to select the best flap configuration. A modular design allowed rapid iterations of these experiments. We confirmed the performance of the best few configurations found during the experiments through fluid simulations. Finally, we report successful demonstrations of RoboTerp walking on asphalt land, swimming in a pool, and transitioning between uneven rock surface and water in an outdoor creek.

We present a novel stereo vision modeling framework that generates approximate, yet physically-plausible representations of objects rather than creating accurate models that are computationally expensive to generate. Our approach to the modeling of target scenes is based on carefully selecting a small subset of the total pixels available for visual processing. To achieve this, we use the estimation-exploration algorithm (EEA) to create the visual models: a population of three-dimensional models is optimized against a growing set of training pixels, and periodically a new pixel that causes disagreement among the models is selected from the observed stereo images of the scene and added to the training set. We show here that using only 5 % of the available pixels, the algorithm can generate approximate models of compound objects in a scene. Our algorithm serves the dual goals of extracting the 3D structure and relative motion of objects of interest by modeling the target objects in terms of their physical parameters (e.g., position, orientation, shape, etc.), and tracking how these parameters vary with time. We support our claims with results from simulation as well from a real robot lifting a compound object.

This paper presents a glowworm metaphor based distributed algorithm that enables a collection of minimalist mobile robots to split into subgroups, exhibit simultaneous taxis-behavior towards, and rendezvous at multiple radiation sources such as nuclear/hazardous chemical spills and fire-origins in a fire calamity. The algorithm is based on a glowworm swarm optimization (GSO) technique that finds multiple optima of multimodal functions. The algorithm is in the same spirit as the ant-colony optimization (ACO) algorithms, but with several significant differences. The agents in the glowworm algorithm carry a luminescence quantity called luciferin along with them. Agents are thought of as glowworms that emit a light whose intensity is proportional to the associated luciferin. The key feature that is responsible for the working of the algorithm is the use of an adaptive local-decision domain, which we use effectively to detect the multiple source locations of interest. The glowworms have a finite sensor range which defines a hard limit on the local-decision domain used to compute their movements. Extensive simulations validate the feasibility of applying the glowworm algorithm to the problem of multiple source localization. We build four wheeled robots called glowworms to conduct our experiments. We use a preliminary experiment to demonstrate the basic behavioral primitives that enable each glowworm to exhibit taxis behavior towards source locations and later demonstrate a sound localization task using a set of four glowworms

This paper presents a glowworm swarm based algorithm that finds solutions to optimization of multiple optima continuous functions. The algorithm is a variant of a well-known ant-colony optimization (ACO) technique, but with several significant modifications. Similar to how each moving region in the ACO technique is associated with a pheromone value, the agents in our algorithm carry a luminescence quantity along with them. Agents are thought of as glowworms that emit a light whose intensity is proportional to the associated luminescence and have a circular sensor range. The glowworms depend on a local-decision domain to compute their movements. Simulations demonstrate the efficacy of the proposed glowworm based algorithm in capturing multiple optima of a multimodal function. The above optimization scenario solves problems where a collection of autonomous robots is used to form a mobile sensor network. In particular, we address the problem of detecting multiple sources of a general nutrient profile that is distributed spatially on a two dimensional workspace using multiple robots.