ICRA 2017 Papers

In micromanipulation, lots of methods have been developed to manipulate objects in microscale. However, few of them can be applied in both the transportation and the rotation of the micro objects. In this paper, we present a novel method to realize the non-contact transportation and rotation of the micro objects based on the vibration-induced swirl flow. A piezo actuator is set between the glass needle and a metal rod. The sine wave with controlled frequency and amplitude is input into the piezo actuator to drive the glass needle to move circularly, which is caused by resonance of the actuator and the metal rod. We place the glass needle under water and keep a limited distance to the bottom. The circular vibration of the glass needle can generate a swirl flow and low pressure around it. The low pressure can trap and transport the micro objects vertically to the glass needle, and the swirl flow can rotate the objects continuously. Finally, we realize the trap and rotation of micro object with only one piezo actuator. Experiments of transportation and rotation of microbeads are carried out, and the results demonstrate it is a simple, low-cost, effective micromanipulation method.

This paper explores the problem of path planning under uncertainty. Specifically, we consider online receding horizon based planners that need to operate in a latent environment where the latent information can be modelled via Gaussian Processes. Online path planning in latent environments is challenging since the robot needs to explore the environment to get a more accurate model of latent information for better planning later and also achieves the task as quick as possible. We propose UCB style algorithms that are popular in the bandit settings and show how those analyses can be adapted to the online robotic path planning problems. The proposed algorithm trades-off exploration and exploitation in near-optimal manner and has appealing no-regret properties. We demonstrate the efficacy of the framework on the application of aircraft flight path planning when the winds are partially observed.

Part handling in warehouse automation is challenging if a large variety of items must be accommodated and items are stored in unordered piles. To foster research in this domain, Amazon holds picking challenges. We present our system which achieved second and third place in the Amazon Picking Challenge 2016 tasks. The challenge required participants to pick a list of items from a shelf or to stow items into the shelf. Using two deep-learning approaches for object detection and semantic segmentation and one item model registration method, our system localizes the requested item. Manipulation occurs using suction on points determined heuristically or from 6D item model registration. Parametrized motion primitives are chained to generate motions. We present a full-system evaluation during the APC 2016 and component-level evaluations of the perception system on an annotated dataset.

Soft actuators play an important role in producing motions in soft robots, and dielectric elastomers have shown great promise because of their considerable voltage-induced deformation. In particular, air-filled dielectric elastomer actuators have been well studied, where the air inside provides prestretches to improve the actuation range. This paper proposes a network of inflated dielectric elastomer actuators, interconnected via a chamber, with the advantages to be highly deformable and continuously controllable. Theoretical analyses show that the networked design is able to largely postpone the occurrence of material failures of the actuators, resulting in a large and continuous actuation range for their control. We further carried out experiments for validation, and the results were largely in line with the theoretical predictions. These findings essentially provide insight into developing networked soft actuators, for achieving large actuation capability.

Magnetotactic bacteria have the potential to controllably reach stagnant fluids inside the human body and achieve targeted drug delivery. In this application, motion of the magnetotactic bacteria is influenced by the near-surface effects such as the background flows and surface interactions. Here, we provide a hydrodynamic model of bipolarly-flagellated magnetotactic bacteria (Magnetospirillum gryphiswaldense strain MSR-1) based on the resistive-force theory to resemble the helical body and the two flagella bundles, and investigate their swimming characteristics in two environments, i.e., free-space and near flat walls. The free-space is studied using capillary tubes with depth of 200 μm, whereas the effect of the flat walls is investigated using microfluidic chips with depth of 5 μm. We find that the linear speeds of bacteria near- and far-surface are 36±16.4 μm/s (mean±s.d.) and 46±6.8 μm/s, respectively, whereas their respective angular velocities are 12.5±5.7 rad/s and 13.5±5.0 rad/s.

This work presents a multiscale framework to solve a class of stochastic optimal control problems in the context of robot motion planning and control in a complex environment. In order to handle complications resulting from a large decision space and complex environmental geometry, two key concepts are adopted: (a) a diffusion wavelet representation of the Markov chain for hierarchical abstraction of the state space; and (b) a desirability function-based representation of the Markov decision process (MDP) to efficiently calculate the optimal policy. In the proposed framework, a global plan that compressively takes into account the long time/length-scale state transition is first obtained by approximately solving an MDP whose desirability function is represented by coarse scale bases in the hierarchical abstraction. Then, a detailed local plan is computed by solving an MDP that considers wavelet bases associated with a focused region of the state space, guided by the global plan. The resulting multiscale plan is utilized to finally compute a continuous-time optimal control policy within a receding horizon implementation. Two numerical examples are presented to demonstrate the applicability and validity of the proposed approach.

The importance of communication in many multirobot information-gathering tasks requires the availability of reliable communication maps. These provide estimates of the radio signal strength and can be used to predict the presence of communication links between different locations of the environment. In the problem we consider, a team of mobile robots has to build such maps autonomously in a robot-to-robot communication setting. The solution we propose models the signal's distribution with a Gaussian Process and exploits different online sensing strategies to coordinate and guide the robots during their data acquisition. Our methods show interesting operative insights both in simulations and on real TurtleBot 2 platforms.

In the Fundamentals of Laparoscopic Surgery (FLS) standard medical training regimen, the Pattern Cutting task requires residents to demonstrate proficiency by maneuvering two tools, surgical scissors and tissue gripper, to accurately cut a circular pattern on surgical gauze suspended at the corners. Accuracy of cutting depends on tensioning, wherein the gripper pinches a point on the gauze in R3 and pulls to induce and maintain tension in the material as cutting proceeds. An automated tensioning policy maps the current state of the gauze to output a direction of pulling as an action. The optimal tensioning policy depends on both the choice of pinch point and cutting trajectory. We explore the problem of learning a tensioning policy conditioned on specific cutting trajectories. Every timestep, we allow the gripper to react to the deformation of the gauze and progress of the cutting trajectory with a translation unit vector along an allowable set of directions. As deformation is difficult to analytically model and explicitly observe, we leverage deep reinforcement learning with direct policy search methods to learn tensioning policies using a finite-element simulator and then transfer them to a physical system. We compare the Deep RL tensioning policies with fixed and analytic (opposing the error vector with a fixed pinch point) policies on a set of 17 open and closed curved contours in simulation and 4 patterns in physical experiments with the da Vinci Research Kit (dVRK). Our simulation results suggest that learning to tension with Deep RL can significantly improve performance and robustness to noise and external forces.

Robot warehouse automation has attracted significant interest in recent years, perhaps most visibly in the Amazon Picking Challenge (APC) [1]. A fully autonomous warehouse pick-and-place system requires robust vision that reliably recognizes and locates objects amid cluttered environments, self-occlusions, sensor noise, and a large variety of objects. In this paper we present an approach that leverages multiview RGB-D data and self-supervised, data-driven learning to overcome those difficulties. The approach was part of the MIT-Princeton Team system that took 3rd- and 4th-place in the stowing and picking tasks, respectively at APC 2016. In the proposed approach, we segment and label multiple views of a scene with a fully convolutional neural network, and then fit pre-scanned 3D object models to the resulting segmentation to get the 6D object pose. Training a deep neural network for segmentation typically requires a large amount of training data. We propose a self-supervised method to generate a large labeled dataset without tedious manual segmentation. We demonstrate that our system can reliably estimate the 6D pose of objects under a variety of scenarios. All code, data, and benchmarks are available at http://apc.cs.princeton.edu/

A fundamental task of automated guided vehicles is transporting heavy payloads. These payloads are often given in the form of large containers that are mounted onto a cart with four caster wheels. In this paper we investigate a combined detection and control architecture that allows an AGV to reliably detect and acquire such containers at any location, independently of a global localization system. We propose a solution using a horizontally mounted 2D laser scanner and a forward facing 3D time-of-flight camera to detect the payload. Furthermore we demonstrate the algorithm on an asymmetric AGV that consists of a differentially driven base and a trailer with a lifting unit.

The multi-robot path planning problem has been extensively studied for the cases of flying and driving vehicles. However, path planning for the case of vehicles that can both fly and drive has not yet been considered. Driving robots, while stable and energy efficient, are limited to mostly flat terrain. Quadcopters, on the other hand, are agile and highly mobile but have low energy efficiency and limited battery life. Combining a quadcopter with a driving mechanism presents a path planning challenge by enabling the selection of paths based off of both time and energy consumption. In this paper, we introduce a framework for multi-robot path planning for a swarm of flying-and-driving vehicles. By putting a lightweight driving platform on a quadcopter, we create a robust vehicle with an energy efficient driving mode and an agile flight mode. We extend two algorithms, priority planning with Safe Interval Path Planning and a multi-commodity network flow ILP, to accommodate multimodal locomotion, and we show that these algorithms can indeed plan collision-free paths for flying-and-driving vehicles on 3D graphs. Finally, we demonstrate that our system is able to plan paths and control the motions of 8 of our vehicles in a miniature town.

Autonomous underwater vehicles (AUVs) are cost- and time-efficient systems for environmental sampling. Informative adaptive sampling has been shown to be an effective method of sampling a lake or ocean for environmental modeling. In this paper, we focus on multi-robot coordination for informative adaptive sampling. We use a dynamic Voronoi partitioning approach whereby the vehicles, in a decentralized fashion, repeatedly calculate weighted Voronoi partitions for the space. Each vehicle then runs informative adaptive sampling within their partition. The vehicles can request surfacing events to share data between vehicles. Simulation results show that the addition of the coordination with dynamic Voronoi partitioning results in obtaining higher quality models faster. Thus we created a decentralized, multi-robot coordination approach for informative, adaptive sampling of unknown environments.

Bio-mimetic robots can interact with groups of animals in bio-hybrid systems to study their behaviour by producing calibrated stimuli and by analysing their responses. Integrating a group of robots into a group of animals to mimic their behaviour is challenging, both in terms of robotic hardware design and robot control. In particular, the robots must be able to react in real-time to the animal changes of behaviour. This implies the need to adequately track and identify animal behaviour. In this paper, we present a novel framework to control several bio-mimetic robots to integrate into groups of fish. Our framework is able to track the position of the fish and robots in real-time. The robots are driven by a bio-mimetic model of fish behaviour from the literature. We show that our multi-robot system can successfully integrate into groups of fish with closed-loop interactions between the robots and the fish.

A team of robots sharing a common goal can benefit from coordination of the activities of team members, helping the team to reach the goal more reliably or quickly. We address the problem of coordinating the actions of a team of robots with periodic communication capability executing an information gathering task. We cast the problem as a multi-agent optimal decision-making problem with an information theoretic objective function. We show that appropriate techniques for solving decentralized partially observable Markov decision processes (Dec-POMDPs) are applicable in such information gathering problems. We quantify the usefulness of coordinated information gathering through simulation studies, and demonstrate the feasibility of the method in a real-world target tracking domain.

We present an efficient approach to plan action sequences for a team of robots from a single finite LTL mission specification. The resulting execution strategy is proven to solve the given mission with minimal team costs, e.g., with shortest execution time. For planning, an established graph-based search method based on the multi-objective shortest path problem is adapted to multi-robot planning and extended to support resource constraints. We further improve planning efficiency significantly for missions which consist of independent parts by using previous results regarding LTL decomposition. The efficiency and practicality of the ROS implementation of our approach is demonstrated in example scenarios.

We present a method for the design optimization of a soft, inflatable robot. The method described utilizes a multi-objective fitness function together with custom, platform-specific metrics related to the dexterity and load-bearing capacity of inflatable manipulators. Candidate designs are scored by computing these metrics at many randomly generated configurations and then by appropriately combining these scores within the multi-objective optimization framework. High performing designs are propagated through a genetic algorithm. The final result is a set of diverse, optimal designs lying along a Pareto front spanning the design space. By examining variations and trade-offs within this set, a designer can more appropriately choose design parameters for a target application. This is especially relevant for robots with many design parameters that can quickly be manufactured as is the case with emerging, soft robot technologies.

We propose a multi-objective optimization algorithm to allocate tasks and plan paths for a team of UAVs. The UAVs must find a target in a bounded area and then continuously communicate the target information to the ground personnel. Our genetic algorithm approach aims to minimize the mission completion time, which includes the time to find the target (area coverage) and the time to setup a communication path (network connectivity). We evaluate strategies using a data mule, a relay chain, and a novel hybrid approach to communicate with the ground personnel. The algorithm can be tuned to prioritize coverage or connectivity, depending on the mission demands. Simulation results show reduced overall mission completion times (up to 65%), with more improvement as the UAV density increases.

In this paper, we exploit the intrinsic relation between different adjective labels and develop a novel multilabel dictionary learning and sparse coding method which is improved by introducing the structured output association information. Such a method makes use of the label correlation information and is more suitable for the multi-label tactile understanding task. In addition, we develop a globally-convergent iterative algorithms to solve the dictionary learning problem. Finally, we perform extensive experimental validations on the public available tactile sequence dataset PHAC-2 and show the advantages of the proposed method.

Joint symbolic and geometric planning is one of the core challenges in robotics. We address the problem of multi-agent cooperative manipulation, where we aim for jointly optimal paths for all agents and over the full manipulation sequence. This joint optimization problem can be framed as a logic-geometric program. Existing solvers lack several features (such as consistently handling kinematic switches) and efficiency to handle the cooperative manipulation domain. We propose a new approximate solver scheme, combining ideas from branch-and-bound and MCTS and exploiting multiple levels of bounds to better direct the search. We demonstrate the method in a scenario where a Baxter robot needs to help a human to reach for objects.