IROS 2016 Papers

Autonomous service mobile robots need to consistently, accurately, and robustly localize in human environments despite changes to such environments over time. Episodic non-Markov Localization addresses the challenge of localization in such changing environments by classifying observations as arising from Long-Term, Short-Term, or Dynamic Features. However, in order to do so, EnML relies on an estimate of the Long-Term Vector Map (LTVM) that does not change over time. In this paper, we introduce a recursive algorithm to build and update the LTVM over time by reasoning about visibility constraints of objects observed over multiple robot deployments. We use a signed distance function (SDF) to filter out observations of short-term and dynamic features from multiple deployments of the robot. The remaining long-term observations are used to build a vector map by robust local linear regression. The uncertainty in the resulting LTVM is computed via Monte Carlo resampling the observations arising from long-term features. By combining occupancy-grid based SDF filtering of observations with continuous space regression of the filtered observations, our proposed approach builds, updates, and amends LTVMs over time, reasoning about all observations from all robot deployments in an environment. We present experimental results demonstrating the accuracy, robustness, and compact nature of the extracted LTVMs from several long-term robot datasets.

The effectiveness of robot interaction depends on the robot's ability to perform task-relevant actions and on the degree to which it is able to predict the outcomes of these actions. In this paper we argue that the two learning problems - learning actions and learning forward models - must be tightly coupled for each of them to be successful. We present an approach that is able to learn a set of continuous action parameters and relational forward models from the robot's own experience. We formalize our approach as simultaneously clustering experiences in a continuous and a relational representation. Our experiments in a simulated manipulation experiment show that this form of coupled subsymbolic and symbolic learning is required for the robot to acquire task-relevant action capabilities.

This paper presents a coordination controller for the Dual-SLIP model, a novel template for quadrupedal steady and transitional running. The model consists of a pair of “physically-unconnected” Spring-Loaded Inverted Pendulums (SLIPs), each representing a part of the body of a quadruped (see Figure 1). For this model, we propose a spatio-temporal coordination controller that describes the evolution of coordination parameters by simple difference equations. A “time-aware” deadbeat low-level controller is also proposed to realizing the generated control specifications in each SLIP individually. Evaluation of the proposed coordination controller for the Dual-SLIP model in simulation shows that even with remarkably off-phase initial conditions and ground height variation disturbances, quadrupedal bounding, pronking and different transitions between them can be realized.

With the rapid development of robotics, dual-arm robots have been more and more widely used. Compared with the traditional single manipulator, it is very challenging for a dual-arm robot in modelling, planning and control. In this paper, we propose two compliance control methods for dual arm coordination to meet different requirements of fine manipulation tasks, such as payload carrying, assembly and repairing. The first method is called master-slave force control strategy, and the second is shared force control strategy. For the former, the desired trajectory and operational force of master arm are given in advance. Then that of slave arm are calculated from the closed-chain constraint equation. On the contrary, the two arms can be controlled in shared mode, that is to say, the desired trajectory and operational force of the end-effectors of dual arms are decomposed from the closed-chain constraint equation directly. The coordinated kinematic and dynamic equations of dual-arm robot system are established by considering the closed-chain constraint relationship. According to the force balance equation of the objective payload, the common force is decomposed into the desired end-effector force of each manipulator. Finally, the control algorithms are verified by simulation and experiment.

Dynamic movement primitives prove to be a useful and effective way to represent a movement of a given agent. However, the original DMP formulation does not take the interaction among multiple agents into the consideration. Thus, many researchers focus on the development of a coupling term for the underlying dynamical system and its associated learning strategies. The result is highly dependent on the quality of the learning methods. In this paper, we present a new way to formulate and realize interactive movement primitive in a leader-follower configuration, where the relationship between the follower and the leader is explicitly represented via the new formulation. This new formulation does not only simplify the learning process, but it also meets the requirements of several applications. We separately tested our new formulation in the context of the handover task and the wiping task. The results prove the flexibility and simplicity of the new formulation.

This paper addresses the problem of cooperative aerial transportation of an object using a team of quadrotors. The approach presented to solve this problem accounts for the full dynamics of the system and it is inspired by the literature on reconfigurable cable-driven parallel robots (RCDPR). Using the modelling convention of RCDPR it is derived a direct relation between the motion of the quadrotors and the motion of the payload. This relation makes explicit the available internal motion of the system, which can be used to automatically achieve additional tasks. The proposed method does not require to specify a priory the forces in the cables and uses a tension distribution algorithm to optimally distribute them among the robots. The presented framework is also suitable for online teleoperation. Physical simulations with a human-in-the-loop validate the proposed approach.

In this paper, we propose a bilateral tele-operation scheme for cooperative aerial manipulation in which a human operator drives a team of Vertical Take-Off and Landing (VTOL) aerial vehicles, that grasped an object beforehand, and receives a force feedback depending on the states of the system. For application scenarios in which dexterous manipulation by each robot is not necessary, we propose using a rigid tool attached to the vehicle through a passive spherical joint, equipped with a simple adhesive mechanism at the tool-tip that can stick to the grasped object. Having more than two robots, we use the extra degrees of freedom to find the optimal force allocation in term of minimum power and forces smoothness. The human operator commands a desired trajectory for the robot team through a haptic interface to a pose controller, and the output of the pose controller along with system constraints, e.g., VTOL limited forces and contact maintenance, defines the feasible set of forces. Then, an on-line optimization allocates forces by minimizing a cost function of forces and their variation. Finally, propeller thrusts are computed by a dedicated attitude and thrust controller in a decentralized fashion. Human/Hardware in the loop simulation study shows efficiency of the proposed scheme, and the importance of haptic feedback to achieve a better performance.

Pneumatic actuators have inherent compliance and hence they are very interesting for applications involving interaction with environment or human. But controlling such kind of actuators is not trivial. The paper presents an implementation of iterative Linear Quadratic regulator (iLQR) based optimal control framework to control an anthropomorphic arm with each joint actuated by an agonist-antagonistic pair of Mckibben artificial muscles. The method is applied to positioning tasks and generation of explosive movements by maximizing the link speed. It is then compared to traditional control strategies to justify that optimal control is effective in controlling the position in highly non-linear pneumatic systems. Also the importance of varying compliance is highlighted by repeating the tasks at different compliance level. The algorithm validation is reported here by several simulations and hardware experiments in which the shoulder and elbow flexion are controlled simultaneously.

This paper presents an improved force-free control method based on current, which can be applied to industrial articulated robotic arms with large mass and large friction torque for direct teaching. Three kinds of torques that influence direct teaching are analyzed, and thus a calibration method and a compensation model are proposed. The model has been demonstrated effective through experiments. Considering the issue of large inertia, some security strategies are proposed at last and also well testified.

Multirotor unmanned aerial vehicles (UAVs) are rapidly gaining popularity for many applications. However, safe operation in partially unknown, unstructured environments remains an open question. In this paper, we present a continuous-time trajectory optimization method for real-time collision avoidance on multirotor UAVs. We then propose a system where this motion planning method is used as a local replanner, that runs at a high rate to continuously recompute safe trajectories as the robot gains information about its environment. We validate our approach by comparing against existing methods and demonstrate the complete system avoiding obstacles on a multirotor UAV platform.

Automated driving is a safety critical process, which requires complex decision making. In order to validate driving decisions, it is possible to maintain at all times a contingency maneuver, which transfers the vehicle to a safe standstill, if other decision making processes fail. In this paper we present a motion planner, which computes contingency maneuvers for an automated vehicle in a 0.1[s] time frame. A discrete set of motion primitives is assembled in a heuristic best-first search. In order to speed up the search, an obstacle sensitive heuristic is applied, which maintains properties of bounded sub-optimality and completeness. A run-time comparison with and without the obstacle sensitive heuristic is presented on two exemplary collision avoidance scenarios.

This paper focuses on the detection of pedestrian crossing intention to improve the situation awareness for autonomous driving in urban environments. A new definition of pedestrian crossing intention is discussed, which allows self-driving vehicles to identify pedestrians, whose intended actions are relevant for the own behavior planning, at an early stage. We propose a context-based feature descriptor in combination with a SVM classifier for detecting this. The descriptor captures the movement of a pedestrian relative to the road and the spatial layout of other scene elements in a generic manner. The performance of the feature descriptor is evaluated in relation to various SVM setups. Feasibility of the approach is demonstrated with data captured on-board of a vehicle in real inner-city traffic. The evaluation of the classification results confirms, that context-based data is a promising indicator for pedestrian crossing intention and that the proposed feature descriptor is capable of representing this. It is further shown that a lack of information about the pedestrian's posture and body movement results in a delayed detection of the pedestrians changing their crossing intention when compared to a human observer.

This paper proposes a new approach to robotic manipulation planning based on the contact between a set of objects, robots and surfaces. We consider making or breaking contact as the most abstract, yet representative element of a manipulation task. Using this paradigm, a robotic manipulation planner has been developed. Given an environment with robots and objects, a manipulation graph is generated by a set of rules and the available geometrical information. Next, the object manipulation planning is formulated as a graph search problem. Paths on this graph divide a complex manipulation task into sub-tasks, followed by low-level path planning and controller assignment for each sub-task. By sequentially executing these controllers in a hybrid fashion, one achieves the overall manipulation task.

Achieving high spatial resolution in contact sensing for robotic manipulation often comes at the price of increased complexity in fabrication and integration. One traditional approach is to fabricate a large number of taxels, each delivering an individual, isolated response to a stimulus. In contrast, we propose a method where the sensor simply consists of a continuous volume of piezoresistive elastomer with a number of electrodes embedded inside. We measure piezoresistive effects between all pairs of electrodes in the set, and count on this rich signal set containing the information needed to pinpoint contact location with high accuracy using regression algorithms. In our validation experiments, we demonstrate submillimeter median accuracy in locating contact on a 10mm by 16mm sensor using only four electrodes (creating six unique pairs). In addition to extracting more information from fewer wires, this approach lends itself to simple fabrication methods and makes no assumptions about the underlying geometry, simplifying future integration on robot fingers.

Manipulation tasks often require robots to make contact between a grasped tool and another object in the robot's environment. The ability to detect and estimate the positions and directions of these contact points is crucial for monitoring the progress of the task, and detecting failures. In this paper, we present a data-driven approach for detecting and localizing contacts between a grasped object and the environment using tactile sensing. We explore framing the contact localization as both a regression and a classification problem and train neural networks accordingly to estimate the contact parameters. We also compare the neural networks with Gaussian process regression and support vector machine classification with spatio-temporal hierarchical matching pursuit feature learning. We evaluate the presented approach using hundreds of contact events on eighteen objects with different shapes, sizes and material properties. The experiments show that the neural network approach can learn to localize contact events for individual objects with a mean absolute error of less than 2.5 cm for the positions and less than 10° for the directions.

This work exploits modeling spatial correlation in 2.5D data using Gaussian Processes (GPs), and produces constrained sampling realizations on these models to improve certainty in the predictions by means of integrating additional sparse information. Data organized in 2.5D such as elevation and thickness maps has been extensively studied in the fields of robotics and geostatistics. These maps are typically represented as a probabilistic 2D grid that stores an estimated value (height or thickness) for each cell. With the increasing popularity and deployment of robotic devices for infrastructure inspection, 2.5D data becomes a common interpretation of the condition of the target being inspected. Modeling the spatial dependencies and making inferences on new grid locations is a common task that has been addressed using GPs, but inference results on locations which are weakly correlated with the training data are generally not sufficiently informative and distinctly uncertain. The predictive capability of the proposed framework, which is applicable to any 2.5D data, is demonstrated with field inspection data from pipelines. Specifically, sparse and complementary measurements from alternative sensing modalities have been incorporated into the model to predict in more detail local thickness conditions where GP training data is limited. The output of this work aims to probabilistically present variations of the target in the case that both accuracy and reasonable diversity are of significant interest.

Many robotic applications, especially if humans are involved, require the robot to adhere to certain joint, workspace, velocity or force limits while simultaneously executing a task. In this paper, we introduce a control structure, which merges an arbitrary desired robot behavior with given constraints. Using a quadratic program (QP), control barrier functions (CBFs) are combined with an arbitrary nominal control law, which determines the desired behavior. The CBFs enforce the constraints, overruling nominal control whenever necessary. We show that the concept is applicable with arbitrary numbers of constraints and any nominal control law. In order to illustrate the capabilities of the approach, the control scheme is applied to an anthropomorphic manipulator, which is constrained by static as well as moving constraints.

The objective of this study is to design a human-robots system that takes into account the non-deterministic nature of the human operator's behavior. Such a system is implemented in a proof of concept scenario relying on a (MO)MDP decision framework that takes advantage of an eye-tracker device to estimate the cognitive availability of the human operator, and, some human operator's inputs to deduce where he is focusing his attention. An experiment was conducted with ten participants interacting with a team of autonomous vehicles in a Search & Rescue scenario. Our results demonstrate the advantages of considering the cognitive availability of a human operator in such a complex context and also the interest of using such a decisional framework that can formally integrate the non-deterministic outcomes which model the human behavior.

Increasing unmanned aerial vehicle (UAV) capabilities and decreasing costs have facilitated growing interest in the development of large, multi-UAV systems, or swarms. The constrained communications environments in which these swarms operate, however, have limited the development of behaviors that require a high degree of deliberative coordination. This work presents two algorithms that use a consensus-algorithm approach to reliably exchange information throughout large swarms as a means of facilitating swarm behavior coordination. Results from experiments conducted in simulation and live-fly exercises are presented and discussed.