IROS 2015 Papers

Sensitivity Amplification Control (SAC) algorithm was first proposed in the augmentation applications of Berkeley Lower Extremity Exoskeleton (BLEEX). The SAC algorithm is widely used in human augmentation applications since it just need the information from the exoskeleton robot, so that the complexity of exoskeleton system can be reduced greatly. However, the SAC algorithm has two main drawbacks: 1) requiring accurate dynamic models of the exoskeleton, 2) can not manage the variation of interaction dynamics from different walking speed. This paper presents a novel developed learning control strategy based on SAC algorithm. In the proposed Adaptive Sensitivity Amplification Control (ASAC) strategy, the reinforcement learning method is utilized to learn the sensitivity factors online for the sake of handling the variation of interaction dynamics. We demonstrate the control efficiency of ASAC on an one degree-of-freedom (DOF) platform with swing movements first, and then extend it into a HUman-powered Augmentation Lower EXoskeleton (HUALEX). The experimental results show that the proposed ASAC strategy can handle the changing interaction dynamics with less interaction force between the pilot and the exoskeleton as compared with traditional SAC algorithm.

We describe a technique to build an affordance map interactively for robotic tasks. Affordances are predicted by a trained classifier using geometric features extracted from objects. Based on 2D occupancy grid, a Markov Random Field (MRF) model builds an affordance map with relational affordance with neighboring cells. The quality of the affordance map is refined by sequences of interactive manipulations selected from the model to yield the highest reduction in uncertainty.

In robot-assisted upper limb rehabilitation, detecting the intentions of hemiplegic patients is essential towards assisting the patients to actively exercise instead of driving passive motions. Many interactive channels, such as voice, EMG and EEG, have been studied to estimate the motion intentions. However, limitations of these techniques, such as high complexity, have constrained their applications in practice. In this paper, we integrate a virtual environment and a low-cost motion sensor into a novel control strategy to detect motion intentions for a rehabilitation robot. Several bimanual motion sequences are intuitively programmed by a professional therapist for subjects to repeat. The strategy uses the unaffected arm and the programmed motion sequence to estimate the motion intentions of the affected arm. We adopt this strategy in Mirror Therapy, a widely-practised therapeutic intervention method. Experiments have been conducted to validate the control strategy.

Real-world robotic systems have to perform reliably in uncertain and dynamic environments. State-of-the-art cognitive robotic systems use an abstract symbolic representation of the real world for high-level reasoning. Some aspects of the world, such as object dynamics, are inherently difficult to capture in an abstract symbolic form, yet they influence whether the executed action will succeed or fail. This paper presents an integrated system that uses a physics-based simulation to predict robot action results and durations, combined with a Hierarchical Task Network (HTN) planner and semantic execution monitoring. We describe a fully integrated system in which a Semantic Execution Monitor (SEM) uses information from the planning domain to perform functional imagination. Based on information obtained from functional imagination, the robot control system decides whether it is necessary to adapt the plan currently being executed. As a proof of concept, we demonstrate a PR2 able to carry tall objects on a tray without the objects toppling. Our approach achieves this by simulating robot and object dynamics. A validation shows that robot action results in simulation can be transferred to the real world. The system improves on state-of-the-art AI plan-based systems by feeding simulated prediction results back into the execution system.

This paper presents a method for integrating a cooperative manipulation task in the design of dynamic walking motions for an underactuated bipedal robot. Applications that involve physical interaction between a walking biped and a leading human (or robot) collaborator, require that the biped exhibits compliance at the port of interaction with the collaborator, while at the same time be capable of adjusting its stepping pattern in response to the interaction forces developed. To achieve these objectives, the proposed method combines impedance control of the biped's arm with position control of its legs in a way that the closed-loop system adapts its stepping pattern in accordance with the collaborator's intentions. The method is applied in the case of a bipedal robot model walking over flat ground and up and down stairs of known geometry under the influence of a trajectory that is unknown to the biped and represents the intention of a collaborator.

We propose information-theoretic strategies for Occupancy Grid (OG) compression to enable high-speed exploration on computationally constrained mobile robots. We first formulate optimal lossy compression for OGs based on the Principle of Relevant Information. The solution to this formulation is a simple compression algorithm that is motivated by rate distortion theory. We then compress OGs to different resolutions and develop a second optimization based on the Information Bottleneck method that chooses a resolution simultaneously maximizing compression and minimizing loss of information from the robot's sensor measurements. On computationally constrained systems, the resulting reduction in computational complexity enables planning over longer predictive horizons, leading to higher-speed operation. Using these techniques to adaptively optimize OG resolution as the robot enters a new area causes it to autonomously slow down in obstacle-dense locations and speed up in open expanses. We simulate and experimentally evaluate mutual information-based exploration through cluttered indoor environments with exploration rates that adapt based on environment complexity, leading to an order-of-magnitude increase in the maximum rate of exploration in contrast to non-adaptive techniques given the same finite computational resources.

We propose an algorithm that enables robots to improve their spatial-semantic representation of an environment by engaging users in dialog during a guided tour. The algorithm selects the best information gathering actions in the form of targeted questions that reduce the ambiguity over the grounding of user-provided natural language descriptions (e.g., “The kitchen is down the hallway”). These questions include those that query the robot's local surround (e.g., “Are we in front of the kitchen?”) as well as areas distant from the robot (e.g., “Is the lounge near the conference room?”). Our algorithm treats dialog as an optimization problem that seeks to balance the information-theoretic value of candidate questions with a measure of cost associated with dialog. In this manner, the algorithm determines the best questions to ask based upon the expected entropy reduction, while accounting for the burden on the user. We evaluate entropy reduction for a joint distribution over a hybrid metric, topological, and semantic representation of the environment learned from user-provided descriptions and the robot's sensor data during the guided tour. We demonstrate that, by asking deliberate questions of the user, the method significantly improves the accuracy of the learned map.

Robot perception is generally viewed as the interpretation of data from various types of sensors such as cameras. In this paper, we study indirect perception where a robot can perceive new information by making inferences from non-visual observations of human teammates. As a proof-of-concept study, we specifically focus on a door detection problem in a stealth mission setting where a team operation must not be exposed to the visibility of the team's opponents. We use a special type of the Noisy-OR model known as BN2O model of Bayesian inference network to represent the inter-visibility and to infer the locations of the doors, i.e., potential locations of the opponents. Experimental results on both synthetic data and real person tracking data achieve an F-measure of over .9 on average, suggesting further investigation on the use of non-visual perception in human-robot team operations.

Unmanned construction machines are used after disasters. Compared with manned construction, time efficiency is lower because of incomplete visual information, communication delay, and lack of tactile experience. We have developed an autonomous camera control system to supply appropriate visual information. In order to inform operators the potential data in the views, we introduced several augmented reality (AR) elements to induce visual attention to suitable images in a scenario. The purpose of this study is to develop an attention inducement system using AR technique and evaluate it under different conditions. We first improve our autonomous camera control system and then implement several kinds of AR items suitable for each work situation. The experimental results conducted using our virtual reality simulator confirm that AR items can supply a better positional relationship between machine and objects in the environment which makes operator handle the conditions as experienced. The results from eye-tracker data also indicate that AR items can induce visual attention to images suitable for situations.

We consider the problem of indoor human trajectory identification using odometry data from smartphone sensors. Given a segmented trajectory, a simplified map of the environment, and a set of error thresholds, we implement a map-matching algorithm in a urban setting and analyze the accuracy of the resulting path. We also discuss aggregation of user step data into a segmented trajectory. Besides providing an interesting application of learning human motion in a constrained environment, we examine how the uncertainty of the snapped trajectory varies with path length. We demonstrate that as new segments are added to a path, the number of possibilities for earlier segments is monotonically non-increasing. Applications of this work in an urban setting are discussed, as well as future plans to develop a formal theory of odometry-based map-matching.

Urban reconstruction from a video captured by a surveying vehicle constitutes a core module of automated mapping. When computational power represents a limited resource and, a detailed map is not the primary goal, the reconstruction can be performed incrementally, from a monocular video, carving a 3D Delaunay triangulation of sparse points; this allows online incremental mapping for tasks such as traversability analysis or obstacle avoidance. To exploit the sharp edges of urban landscape, we propose to use a Delaunay triangulation of Edge-Points, which are the 3D points corresponding to image edges. These points constrain the edges of the 3D Delaunay triangulation to real-world edges. Besides the use of the Edge-Points, a second contribution of this paper is the Inverse Cone Heuristic that preemptively avoids the creation of artifacts in the reconstructed manifold surface. We force the reconstruction of a manifold surface since it makes it possible to apply computer graphics or photometric refinement algorithms to the output mesh. We evaluated our approach on four real sequences of the public available KITTI dataset by comparing the incremental reconstruction against Velodyne measurements.

In this paper, we propose a novel online multiobject learning and detection algorithm. From single seed images of the target objects, our algorithm detects these objects in the input sequence, and incrementally updates the databases with the detection results. Reasonably sized databases are maintained as graphs of the registered images, while new views of the objects are added as the detection proceeds. The importance of the registered images is computed using our ranking algorithm, and redundant images are pruned from the database. The proposed method fully utilizes graphical representation to detect and recognize objects. A 3D model of a candidate object is built on-the-fly using the retrieved images, and initially undetected features are hallucinated for further matching and verification. This process improves the detection performance compared to the baseline algorithm. Object/background feature classification and object-likelihood maps effectively keep noisy background features from being added to the databases. The experimental results demonstrate that the proposed algorithm efficiently maintains the object databases and achieves better performance.

Aquiring reliable depth maps is an essential prerequisite for accurate and incremental 3D reconstruction used in a variety of robotics applications. Depth maps produced by affordable Kinect-like cameras have become a de-facto standard for indoor reconstruction and the driving force behind the success of many algorithms. However, Kinect-like cameras are less effective outdoors where one should rely on other sensors. Often, we use a combination of a stereo camera and lidar, however, process the acquired data in independent pipelines which generally leads to sub-optimal performance since both sensors suffer from different drawbacks. In this paper, we propose a probabilistic model that efficiently exploits complementarity between different depth-sensing modalities for incremental dense scene reconstruction. Our model uses a piecewise planarity prior assumption which is common in both the indoor and outdoor scenes. We demonstrate the effectiveness of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense reconstruction of a number of scenes.

This paper proposes a method to increase the impedance range of admittance-type haptic interfaces. Admittance-type haptic interfaces are used in various applications that typically require interaction with high impedance virtual environments. However, the performance of admittance haptic interfaces is often judged by the lower boundary of the impedance that can be achieved without stability problem; in particular, minimum displayable inertia. It is well known that rendering the low value of inertia makes the admittance-type haptic interfaces unstable easily. This paper extends Time Domain Passivity Approach (TDPA) to lower down the minimum achievable inertia in an Admittance-type haptic interface. To use the well-developed TDPA framework, an admittance haptic interface should be represented in network domain with clear energy flows, which was not straightforward due to unclear causality. Therefore by introducing dependent effort and flow source concept, the admittance type haptic interface is represented in electrical network domain. This network representation allows us to have clear causality, and consequently allowing to implement TDPA. The proposed idea was experimentally verified, and found successful in bringing down the minimum inertia 10 times lower than without TDPA case.

Interest in the area of collaborative Unmanned Aerial Vehicles (UAVs) in a Multi-Agent System is growing to compliment the strengths and weaknesses of the human-machine relationship. To achieve effective management of multiple heterogeneous UAVs, the status model of the agents must be communicated to each other. This paper presents the effects on operator Cognitive Workload (CW), Situation Awareness (SA), trust and performance by increasing the autonomy capability transparency through text-based communication of the UAVs to the human agents. The results revealed a reduction in CW, increase in SA, increase in the Competence, Predictability and Reliability dimensions of trust, and the operator performance.

This article presents an inchworm climbing robot that is designed with switchable magnets and a single DOF arm. The InchwormClimber works on ferromagnetic structures and consumes little energy when climbing and can descend safely with almost zero energy consumption. Furthermore, considering the critical role of the adhesion unit in the overall functionality of the robot (weight, climbing speed and the payload), we optimized the switchable magnet unit for a higher adhesion force per mass unit.

In this paper, we describe design and experimental results of repetitive calibration of an holonomic inchworm robot based on an inverse trajectory analysis of a tip of a probe for microscopic operations. The mobile robot has two U-shaped electromagnets and four piezoelectric actuators (PAs) for obtaining 3-degrees-of-freedom (3DoF) motion on well-polished ferromagnetic surfaces. We have proposed the kinematic model to get relationship among four input voltages to PAs and three displacements of the robot at a half step. We have also solved the inverse trajectory analysis of the probe to convert the motion errors of the probe into those of the robot. Moreover, we have proposed repetitive calibration formulas to calibrate 3DoF motion of the probe under a microscope simultaneously. In experiments, we have checked that the proposed formulas are surely working for decreasing the motion errors at straight motion although rotation around the tip is hard to calibrate because of its posture measuring error of an image processor. We discuss compact and flexible microscopic operations.

In this work we propose a sliding mode controller for in-hand manipulation that repositions a tool in the robot's hand by using gravity and controlling the slippage of the tool. In our approach, the robot holds the tool with a pinch grasp and we model the system as a link attached to the gripper via a passive revolute joint with friction, i.e., the grasp only affords rotational motions of the tool around a given axis of rotation. The robot controls the slippage by varying the opening between the fingers in order to allow the tool to move to the desired angular position following a reference trajectory. We show experimentally how the proposed controller achieves convergence to the desired tool orientation under variations of the tool's inertial parameters.

In the present paper, we propose a method for in-air knotting by a dual-arm, multi-finger robot. Most previous studies about knotting by robots assume that the rope is placed on a table. However, in-air knotting requires more skillful hand manipulations, such as swapping ropes between the right and left hands. Therefore, we herein focus on hand motion and first extract the essential hand motions for knotting, referred to herein as skill motions, by observing human knotting procedures. Next, hardware with the capability of executing these skill motions is developed. Finally, experiments are conducted to confirm that several types of knots can be tied in the air using the proposed method.