IROS 2020 Papers

Because of their large workspace, robot manipulators have the potential to be used for high precision non-contact manufacturing processes, such as laser cutting or welding, on large complex work pieces. However, most industrial manipulators are not able to provide the necessary accuracy requirements. Mainly because of their flexible structures, they are subject to point to point positioning errors and also vibration errors on a smaller scale. The vibration issues are especially hard to deal with. Many published solutions propose to modify the robot's own control system to deal with these problems. However, most modern control techniques require high fidelity models of the underlying system dynamics, which are quite difficult to obtain for robot manipulators. In this work, we propose an external stabilization unit with an additional set of actuators/sensors to stabilize the process tool, similar to Optical Image Stabilization systems. We show that, because of collocated control, a model of the robot's own dynamic behavior is not needed to achieve high tracking accuracy. We also provide testing results of a prototype stabilizing a dummy tool in two degrees of freedom on a UR10 robot, which reduced its tracking error by two orders of magnitude below 20 micrometers.

To this day, most robots are installed behind safety fences, separated from the human. New use-case scenarios demand for collaborative robots, e.g. to assist the human with physically challenging tasks. These robots are mainly installed in work-environments with limited space, e.g. existing production lines. This brings certain challenges for the control of such robots. The presented work addresses a few of these challenges, namely: stable and safe behaviour in contact scenarios; avoidance of restricted workspace areas; prevention of joint limits in automatic mode and manual guidance. The control approach in this paper extents an Energy-aware Impedance controller by repulsive potential fields in order to comply with Cartesian and joint constraints. The presented controller was verified for a KUKA LBR iiwa 7 R800 in simulation as well as on the real robot.

Underwater communication is extremely challenging for small underwater robots which typically have stringent power and size constraints. In our previous work, we developed an artificial electrocommunication system which could be an alternative for the communication of small underwater robots. This paper further presents a new electrocommunication system that utilizes Binary Frequency Shift Keying (2FSK) modulation and deep-learning-based demodulation for underwater robots. We first derive an underwater electrocommunication model that covers both the near-field area and a large transition area outside of the near-field area. 2FSK modulation is adopted to improve the anti-interference ability of the electric signal. A deep learning algorithm is used to demodulate the electric signal by the receiver. Simulations and experiments show that with the same testing condition, the new communication system outperforms the previous system in both the communication distance and the data transmitting rate. In specific, the newly developed communication system achieves stable communication within the distance of 10 m at a data transfer rate of 5 Kbps with a power consumption of less than 0.1 W. The substantial increase in communication distance further improves the possibility of electrocommunication in underwater robotics.

Earthworm-like soft robots have been widely studied for various applications, such as medical endoscopy and pipeline inspection. Many actuation modes have been chosen to drive the soft robots, including pneumatic actuators, dielectric elastomeric actuators, and shape memory actuators. Pneumatic actuators stand out since the soft robots with pneumatic actuation can produce relatively large forces and displacements with relatively ease of fabrication. Currently, several pneumatic actuators are used to realize elongating movement and anchoring movement of the earthworm for peristaltic motion. More pneumatic actuators not only require more pumps and valves to actuate and control the earthworm, but also lead to less efficient movement control of the earthworm. To address this issue, a new design with integrated single pneumatic actuator and cellular structures is developed to realize elongating movement and anchoring movement of the earthworm-like soft robot in peristaltic motion. With the new design, the simulation model of the new earthworm is developed to simulate both elongating and anchoring movements of the earthworm. A 3D printed prototype of the earthworm-like soft robot is fabricated to validate the proposed design and simulation model. Experimental results show good agreement with the simulation in elongations of peristaltic motion as the differences between the simulated and experimental is 5.8 % in one cycle of the peristaltic motion.

The deployment of a mobile service robot in domestic settings is a challenging task due to the dynamic and unstructured nature of such environments. Successful operation of the robot requires continuous human supervision to update its spatial knowledge about the dynamic environment. Thus, it is essential to develop a human-robot interaction (HRI) strategy that is suitable for novice end users to effortlessly provide task-specific spatial information to the robot. Although several approaches have been developed for this purpose, most of them are not feasible or convenient for use in domestic environments. In response, we have developed an augmented reality (AR) spatial referencing system (SRS), which allows a non-expert user to tag any specific locations on a physical surface to allocate tasks to be performed by the robot at those locations. Specifically, in the AR-SRS, the user provides a spatial reference by creating an AR virtual object with a semantic label. The real-world location of the user-created virtual object is estimated and stored as spatial data along with the user-specified semantic label. We present three different approaches to establish the correspondence between the user-created virtual object locations and the real-world coordinates on an a priori static map of the service area available to the robot. The performance of each approach is evaluated and reported. We also present use-case scenarios to demonstrate potential applications of the AR-SRS for mobile service robots.

Human drone interaction in autonomous navigation incorporates spatial interaction tasks, including reconstructed 3D map from the drone and human desired target position. Augmented Reality (AR) devices can be powerful interactive tools for handling these spatial interactions. In this work, we build an AR interface that displays the reconstructed 3D map from the drone on physical surfaces in front of the operator. Spatial target positions can be further set on the 3D map by intuitive head gaze and hand gesture. The AR interface is deployed to interact with an autonomous drone to explore an unknown environment. A user study is further conducted to evaluate the overall interaction performance.

This paper investigate potential use of augmented reality (AR) for physical human-robot collaboration in large-scale, labour-intensive manufacturing tasks. While it has been shown that use of AR can help increase task efficiency in teleoperative and robot programming tasks involving smaller-scale robots, its use for physical human-robot collaboration in shared workspaces and large-scale manufacturing tasks have not been well-studied. With the eventual goal of applying our AR system to collaborative aircraft body manufacturing, we compare in a user study the use of an AR interface we developed with a standard joystick for human robot collaboration in an experiment task simulating industrial carbon-fibre-reinforced-polymer manufacturing procedure. Results show that use of AR yields reduced task time and physical demand, with increased robot utilization.

In the context of a multi-agent system that uses a Gaussian process to estimate a spatial field of interest, we propose an approach that enables an agent to reduce the amount of data it shares with other agents. The main idea of the strategy is to rigorously assign a novelty metric to each measurement as it is collected, and only measurements that are sufficiently novel are communicated. We consider the ideal scenario where an agent can instantly share novel measurements, and we also consider the more practical scenario in which communication suffers from low bandwidth and is range-limited. For this scenario, an agent can only broadcast an informative subset of the novel measurements when the agent encounters other agents. We explore three different informative criteria for subset selection, namely entropy, mutual information, and a new criterion that reflects the value of a measurement. We apply our approach to three real-world datasets relevant to robotic mapping. The empirical findings show that an agent can reduce the amount of communicated measurements by two orders of magnitude and that the new criterion for subset selection yields superior predictive performance relative to entropy and mutual information.

Programming cooperative tasks for autonomous swarm robotic systems has always been challenging. In this paper, we introduce a concept ‘Actor’, as a virtualization for robot platforms. Every robot platform in the swarm robotic system carries out the task and interacts with others as an Actor. We designed an Actor-based framework for the management of autonomous swarm robotic systems including modules and interfaces for the Actor, the collective Actor, and task management. The Actor-based framework enables task developers to explicitly model cooperative tasks without intricacies about the detailed robotic algorithms or the specific robot brands, and eases the burden on robotic algorithm developers by providing common functionalities. The proposed framework is implemented in C++ and validated quantitatively and qualitatively with a swarm of thirty drones by simulations and a swarm of ten drones by in-field tests.

This work addresses the problem of learning a model of a dynamic environment using many independent Hidden Markov Models (HMMs) with a limited number of observations available per iteration. Many techniques exist to model dynamic environments, but do not consider how to deploy robots to build this model. Additionally, there are many techniques for exploring environments that do not consider how to prioritize regions when resources, in terms of robots to deploy and deployment durations, are limited. Here, we consider an environment model consisting of a series of HMMs that evolve over time independently and can be directly observed. At each iteration, we must determine which HMMs to observe in order to maximize the gain in model accuracy. We present a utility measure that balances a Pearson's χ2 goodness-of-fit of the dynamics model with Mutual Information (MI) to ensure that observations are allocated to maximize the convergence rate of all HMMs, resulting in a faster convergence to higher steady-state model confidence and accuracy than either χ2 or MI alone.

We present a novel algorithm for the multi-robot generalized assignment problem (GAP) with stochastic resource consumption. In this problem, each robot has a resource (e.g., battery life) constraint and it consumes a certain amount of resource to perform a task. In practice, the resource consumed for performing a task can be uncertain. Therefore, we assume that the resource consumption is a random variable with known mean and variance. The objective is to find an assignment of the robots to tasks that maximizes the team payoff. Each task is assigned to at most one robot and the resource constraint for each robot has to be satisfied with very high probability. We formulate the problem as a chance-constrained combinatorial optimization problem and call it the chance-constrained generalized assignment problem (CC-GAP). This problem is an extension of the deterministic generalized assignment problem, which is a NP-hard problem. We design an iterative algorithm for solving CC-GAP in which each robot maximizes its own objective by solving a chance-constrained knapsack problem in an iterative manner. The approximation ratio of our algorithm is (1+α), assuming that the deterministic knapsack problem is solved by an α-approximation algorithm. We present simulation results to demonstrate that our algorithm is scalable with the number of robots and tasks.

Avoiding obstacles in the perceived world has been the classical approach to autonomous mobile robot navigation. However, this usually leads to unnatural and inefficient motions that significantly differ from the way humans move in tight and dynamic spaces, as we do not refrain interacting with the environment around us when necessary. Inspired by this observation, we propose a framework for autonomous robot navigation among movable obstacles (NAMO) that is based on the theory of affordances and contact-implicit motion planning. We consider a realistic scenario in which a mobile service robot negotiates unknown obstacles in the environment while navigating to a goal state. An affordance extraction procedure is performed for novel obstacles to detect their movability, and a contact-implicit trajectory optimization method is used to enable the robot to interact with movable obstacles to improve the task performance or to complete an otherwise infeasible task. We demonstrate the performance of the proposed framework by hardware experiments with Toyota's Human Support Robot.

In real world applications, robotic solutions remain impractical due to the challenges that arise in unknown and unstructured environments. To perform complex manipulation tasks in complex and cluttered situations, robots need to be able to identify the interaction possibilities with the scene, i.e. the affordances of the objects encountered. In unstructured environments with noisy perception, insufficient scene understanding and limited prior knowledge, this is a challenging task. In this work, we present an approach for grasping unknown objects in cluttered scenes with a humanoid robot in the context of a nuclear decommissioning task. Our approach combines the convenience and reliability of autonomous robot control with the precision and adaptability of teleoperation in a semi-autonomous selection of grasp affordances. Additionally, this allows exploiting the expert knowledge of an experienced human worker. To evaluate our approach, we conducted 75 real world experiments with more than 660 grasp executions on the humanoid robot ARMAR-6. The results demonstrate that high-level decisions made by the human operator, supported by autonomous robot control, contribute significantly to successful task execution.

With the advent of intelligent transport, quadrotors are becoming an attractive aerial transport solution during emergency evacuations, construction works etc. During such operations, dynamic variations in (possibly unknown) payload and unknown external disturbances cause considerable control challenges for path tracking algorithms. In fact, the state-dependent nature of the resulting uncertainties makes state-of-the-art adaptive control solutions ineffective against such uncertainties that can be completely unknown and possibly unbounded a priori. This paper, to the best of the knowledge of the authors, proposes the first adaptive control solution for quadrotors, which does not require any a priori knowledge of the parameters of quadrotor dynamics as well as of external disturbances. The stability of the closed-loop system is studied analytically via Lyapunov theory and the effectiveness of the proposed solution is verified on a realistic simulator.

Dnamic System Identification approaches usually heavily rely on evolutionary and gradient-based optimisation techniques to produce optimal excitation trajectories for determining the physical parameters of robot platforms. Current optimisation techniques tend to generate single trajectories. This is expensive, and intractable for longer trajectories, thus limiting their efficacy for system identification. We propose to tackle this issue by using multiple shorter cyclic trajectories, which can be generated in parallel, and subsequently combined together to achieve the same effect as a longer trajectory. Crucially, we show how to scale this approach even further by increasing the generation speed and quality of the dataset through the use of generative adversarial network (GAN) based architectures to produce large databases of valid and diverse excitation trajectories. To the best of our knowledge, this is the first robotics work to explore system identification with multiple cyclic trajectories and to develop GAN-based techniques for scaleably producing excitation trajectories that are diverse in both control parameter and inertial parameter spaces. We show that our approach dramatically accelerates trajectory optimisation, while simultaneously providing more accurate system identification than the conventional approach.

A successful robot-assisted feeding system requires bite acquisition of a wide variety of food items. It must adapt to changing user food preferences under uncertain visual and physical environments. Different food items in different environmental conditions require different manipulation strategies for successful bite acquisition. Therefore, a key challenge is how to handle previously unseen food items with very different success rate distributions over strategy. Combining low-level controllers and planners into discrete action trajectories, we show that the problem can be represented using a linear contextual bandit setting. We construct a simulated environment using a doubly robust loss estimate from previously seen food items, which we use to tune the parameters of off-the-shelf contextual bandit algorithms. Finally, we demonstrate empirically on a robot- assisted feeding system that, even starting with a model trained on thousands of skewering attempts on dissimilar previously seen food items, ϵ-greedy and LinUCB algorithms can quickly converge to the most successful manipulation strategy.

This paper studies the adaptive reliable shortest path (RSP) planning problem in a Gaussian process (GP) regulated environment. With the reasonable assumption that the travel times of the underlying transportation network follow a multi-variate Gaussian distribution, we propose two algorithms namely, Gaussian process reactive path planning (GPRPP), and Gaussian process proactive path planning (GP4), to generate online adaptive routing policies for the reliable shortest path. Both algorithms take advantage of the posterior analytical representation of GPs given past and/or imagined future observations of certain links in the network, and calculate the corresponding adaptive routing strategy for RSP. Theoretical analysis and simulation results (on Sioux Falls Network and Singapore road networks) show the superior performance of GPRPP and GP4 over that of the state of the arts.

We introduce a 3D hand rendering framework to reconstruct a visually realistic hand from a set of fingertip positions. One of the key limitations of wearable fingertip tracking devices used in VR/AR applications is the lack of detailed measurements and tracking of the hand, making the hand rendering difficult. The motivation for this paper is to develop a general framework to render a visually plausible hand given only the fingertip positions. In addition, our framework adjusts the size of a virtual hand based on the fingertip positions and device's structure, and reduces a mismatch between the pose of the rendered and user's hand by retargeting virtual finger motions. Moreover, we impose a new hinge constraint on the finger model to employ a real-time inverse kinematic solver. We show our framework is helpful for performing virtual grasping tasks more efficiently when only the measurements of fingertip positions are available.

A tactile sensor with high spatio-temporal resolution will greatly contribute to improving the performance of object recognition and human interaction in robots. In addition, being able to switch between higher spatial and higher temporal resolution will allow for more versatile sensing. To realize such a sensor, this paper introduces a method of increasing the sensing electrodes and adaptively selecting the grounding conditions in a tomography based tactile sensor. Several types of grounding conditions are proposed and evaluated using spatio-temporal metrics. As a result, the grounding method based on the location of contact had a good balance of temporal resolution (1 ms) and spatial resolution (only 1.55 times larger than using all electrodes as grounding conditions). When reconstructing dynamic contact data, the proposed method was able to obtain a much higher detailed waveform compared to the conventional method. By using the proposed method as default and switching to other grounding methods depending on the purpose of sensing, a versatile tactile sensor with high spatio-temporal resolution can be made.