ICRA 2015 论文列表

We present a robotic agent that learns to derive object grasp stability from touch. The main contribution of our work is the use of a characterization of the shape of the part of the object that is enclosed by the gripper to condition the tactile-based stability model. As a result, the agent is able to express that a specific tactile signature may for instance indicate stability when grasping a cylinder, while cuing instability when grasping a box. We proceed by (1) discretizing the space of graspable object parts into a small set of prototypical shapes, via a data-driven clustering process, and (2) learning a touch-based stability classifier for each prototype. Classification is conducted through kernel logistic regression, applied to a low-dimensional approximation of the tactile data read from the robot's hand. We present an experiment that demonstrates the applicability of the method, yielding a success rate of 89%. Our experiment also shows that the distribution of tactile data differs substantially between grasps collected with different prototypes, supporting the use of shape cues in touch-based stability estimators.

In this paper, we introduce an abstract representation for manipulation actions that is based on the evolution of the spatial relations between involved objects. Object tracking in RGBD streams enables straightforward and intuitive ways to model spatial relations in 3D space. Reasoning in 3D overcomes many of the limitations of similar previous approaches, while providing significant flexibility in the desired level of abstraction. At each frame of a manipulation video, we evaluate a number of spatial predicates for all object pairs and treat the resulting set of sequences (Predicate Vector Sequences, PVS) as an action descriptor. As part of our representation, we introduce a symmetric, time-normalized pairwise distance measure that relies on finding an optimal object correspondence between two actions. We experimentally evaluate the method on the classification of various manipulation actions in video, performed at different speeds and timings and involving different objects. The results demonstrate that the proposed representation is remarkably descriptive of the high-level manipulation semantics.

The selection of a suitable set of visual features for an optimal performance of closed-loop visual control or Structure from Motion (SfM) schemes is still an open problem in the visual servoing community. For instance, when considering integral region-based features such as image moments, only heuristic, partial, or local results are currently available for guiding the selection of an appropriate moment set. The goal of this paper is to propose a novel learning strategy able to automatically optimize online the shape of a given class of image moments as a function of the observed scene for improving the SfM performance in estimating the scene structure. As case study, the problem of recovering the (unknown) 3D parameters of a planar scene from measured moments and known camera motion is considered. The reported simulation results fully confirm the soundness of the approach and its superior performance over more consolidated solutions in increasing the information gain during the estimation task.

In this paper, a robot learning approach is proposed which integrates Visuospatial Skill Learning, Imitation Learning, and conventional planning methods. In our approach, the sensorimotor skills (i.e., actions) are learned through a learning from demonstration strategy. The sequence of performed actions is learned through demonstrations using Visuospatial Skill Learning. A standard action-level planner is used to represent a symbolic description of the skill, which allows the system to represent the skill in a discrete, symbolic form. The Visuospatial Skill Learning module identifies the underlying constraints of the task and extracts symbolic predicates (i.e., action preconditions and effects), thereby updating the planner representation while the skills are being learned. Therefore the planner maintains a generalized representation of each skill as a reusable action, which can be planned and performed independently during the learning phase. Preliminary experimental results on the iCub robot are presented.

Many everyday human skills can be considered in terms of performing some task subject to a set of self-imposed or environmental constraints. In recent years, a number of new tools have become available in the learning and robotics community that allow data from constrained and/or redundant systems to be used to uncover underlying consistent behaviours that may be otherwise masked by the constraints. However, while a wide variety of work for generalisation of movements have been proposed, few have explicitly considered learning the constraints of the motion and ways to cope with unknown environment. In this paper, we propose a method to learn the constraints such that some previously learnt behaviours can be adapted to new environment in an appropriate way. In particular, we consider learning the null space projection matrix of a kinematically constrained system, and see how previously learnt policies can be adapted to novel constraints.

For a mobile manipulator to interact with large everyday objects, such as office tables, it is often important to have dynamic models of these objects. However, as it is infeasible to provide the robot with models for every possible object it may encounter, it is desirable that the robot can identify common object models autonomously. Existing methods for addressing this challenge are limited by being either purely kinematic, or inefficient due to a lack of physical structure. In this paper, we present a physics-based method for estimating the dynamics of common non-holonomic objects using a mobile manipulator, and demonstrate its efficiency compared to existing approaches.

Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in practice, interactions between a human and a robot can consist of many different patterns. To overcome this limitation this paper proposes a Mixture of Interaction Primitives to learn multiple interaction patterns from unlabeled demonstrations. Specifically the proposed method uses Gaussian Mixture Models of Interaction Primitives to model nonlinear correlations between the movements of the different agents. We validate our algorithm with two experiments involving interactive tasks between a human and a lightweight robotic arm. In the first, we compare our proposed method with conventional Interaction Primitives in a toy problem scenario where the robot and the human are not linearly correlated. In the second, we present a proof-of-concept experiment where the robot assists a human in assembling a box.

Kinesthetic teaching is a promising approach to acquire robot skills in an intuitive way. This paper focuses on learning skills that do not solely rely on kinematics but also need to take into account interaction forces. We present three novel concepts towards learning such force interaction skills. Firstly, we determine segments from a small number of continuous kinesthetic demonstrations using contact information. Secondly, we associate each segment with a movement primitive, and determine its composition, i.e., the control variables and reference frames that allow to reproduce the demonstrated task. Lastly, we propose a concept to determine the transitions between the primitives during reproduction. The proposed methods are evaluated on a box pulling and flipping task, and show very good generalization abilities for objects with different geometries, and situations with different object arrangements.

Natural language offers an intuitive and flexible means for humans to communicate with the robots that we will increasingly work alongside in our homes and workplaces. Recent advancements have given rise to robots that are able to interpret natural language manipulation and navigation commands, but these methods require a prior map of the robot's environment. In this paper, we propose a novel learning framework that enables robots to successfully follow natural language route directions without any previous knowledge of the environment. The algorithm utilizes spatial and semantic information that the human conveys through the command to learn a distribution over the metric and semantic properties of spatially extended environments. Our method uses this distribution in place of the latent world model and interprets the natural language instruction as a distribution over the intended behavior. A novel belief space planner reasons directly over the map and behavior distributions to solve for a policy using imitation learning. We evaluate our framework on a voice-commandable wheelchair. The results demonstrate that by learning and performing inference over a latent environment model, the algorithm is able to successfully follow natural language route directions within novel, extended environments.

We present an end-to-end framework for realizing fully automated gait learning for a complex underwater legged robot. Using this framework, we demonstrate that a hexapod flipper-propelled robot can learn task-specific control policies purely from experience data. Our method couples a state-of-the-art policy search technique with a family of periodic low-level controls that are well suited for underwater propulsion. We demonstrate the practical efficacy of tabula rasa learning, that is, learning without the use of any prior knowledge, of policies for a six-legged swimmer to carry out a variety of acrobatic maneuvers in three dimensional space. We also demonstrate informed learning that relies on simulated experience from a realistic simulator. In numerous cases, novel emergent gait behaviors have arisen from learning, such as the use of one stationary flipper to create drag while another oscillates to create thrust. Similar effective results have been demonstrated in under-actuated configurations, where as few as two flippers are used to maneuver the robot to a desired pose, or through an acrobatic motion such as a corkscrew. The success of our learning framework is assessed both in simulation and in the field using an underwater swimming robot.

In whole-body control, joint torques and external forces need to be estimated accurately. In principle, this can be done through pervasive joint-torque sensing and accurate system identification. However, these sensors are expensive and may not be integrated in all links. Moreover, the exact position of the contact must be known for a precise estimation. If contacts occur on the whole body, tactile sensors can estimate the contact location, but this requires a kinematic spatial calibration, which is prone to errors. Accumulating errors may have dramatic effects on the system identification. As an alternative to classical model-based approaches we propose a data-driven mixture-of-experts learning approach using Gaussian processes. This model predicts joint torques directly from raw data of tactile and force/torque sensors. We compare our approach to an analytic model-based approach on real world data recorded from the humanoid iCub. We show that the learned model accurately predicts the joint torques resulting from contact forces, is robust to changes in the environment and outperforms existing dynamic models that use of force/ torque sensor data.

Manipulation of deformable objects often requires a robot to apply specific forces to bring the object into the desired configuration. For instance, tightening a knot requires pulling on the ends, flattening an article of clothing requires smoothing out wrinkles, and erasing a whiteboard requires applying downward pressure. We present a method for learning force-based manipulation skills from demonstrations. Our approach uses non-rigid registration to compute a warping function that transforms both the end-effector poses and forces in each demonstration into the current scene, based on the configuration of the object. Our method then uses the variation between the demonstrations to extract a single trajectory, along with time-varying feedback gains that determine how much to match poses or forces. This results in a learned variable-impedance control strategy that trades off force and position errors, providing for the right level of compliance that applies the necessary forces at each stage of the motion. We evaluate our approach by tying knots in rope, flattening towels, and erasing a whiteboard.

It is expected that autonomous vehicles capable of driving without human supervision will be released to market within the next decade. For user acceptance, such vehicles should not only be safe and reliable, they should also provide a comfortable user experience. However, individual perception of comfort may vary considerably among users. Whereas some users might prefer sporty driving with high accelerations, others might prefer a more relaxed style. Typically, a large number of parameters such as acceleration profiles, distances to other cars, speed during lane changes, etc., characterize a human driver's style. Manual tuning of these parameters may be a tedious and error-prone task. Therefore, we propose a learning from demonstration approach that allows the user to simply demonstrate the desired style by driving the car manually. We model the individual style in terms of a cost function and use feature-based inverse reinforcement learning to find the model parameters that fit the observed style best. Once the model has been learned, it can be used to efficiently compute trajectories for the vehicle in autonomous mode. We show that our approach is capable of learning cost functions and reproducing different driving styles using data from real drivers.

Autonomous learning of object manipulation skills can enable robots to acquire rich behavioral repertoires that scale to the variety of objects found in the real world. However, current motion skill learning methods typically restrict the behavior to a compact, low-dimensional representation, limiting its expressiveness and generality. In this paper, we extend a recently developed policy search method [1] and use it to learn a range of dynamic manipulation behaviors with highly general policy representations, without using known models or example demonstrations. Our approach learns a set of trajectories for the desired motion skill by using iteratively refitted time-varying linear models, and then unifies these trajectories into a single control policy that can generalize to new situations. To enable this method to run on a real robot, we introduce several improvements that reduce the sample count and automate parameter selection. We show that our method can acquire fast, fluent behaviors after only minutes of interaction time, and can learn robust controllers for complex tasks, including putting together a toy airplane, stacking tight-fitting lego blocks, placing wooden rings onto tight-fitting pegs, inserting a shoe tree into a shoe, and screwing bottle caps onto bottles.

Automating repetitive surgical subtasks such as suturing, cutting and debridement can reduce surgeon fatigue and procedure times and facilitate supervised tele-surgery. Programming is difficult because human tissue is deformable and highly specular. Using the da Vinci Research Kit (DVRK) robotic surgical assistant, we explore a “Learning By Observation” (LBO) approach where we identify, segment, and parameterize motion sequences and sensor conditions to build a finite state machine (FSM) for each subtask. The robot then executes the FSM repeatedly to tune parameters and if necessary update the FSM structure. We evaluate the approach on two surgical subtasks: debridement of 3D Viscoelastic Tissue Phantoms (3d-DVTP), in which small target fragments are removed from a 3D viscoelastic tissue phantom; and Pattern Cutting of 2D Orthotropic Tissue Phantoms (2d-PCOTP), a step in the standard Fundamentals of Laparoscopic Surgery training suite, in which a specified circular area must be cut from a sheet of orthotropic tissue phantom. We describe the approach and physical experiments with repeatability of 96% for 50 trials of the 3d-DVTP subtask and 70% for 20 trials of the 2d-PCOTP subtask. A video is available at: http://j.mp/Robot-Surgery-Video-Oct-2014.

We study the use of Predictive State Representation (PSR) for modeling of an in-hand manipulation task through interaction with the environment. We extend the original PSR model to a new domain of in-hand manipulation and address the problem of partial observability by introducing new kernel-based features that integrate both actions and observations. The model is learned directly from haptic data and is used to plan series of actions that rotate the object in the hand to a specific configuration by pushing it against a table. Further, we analyze the model's belief states using additional visual data and enable planning of action sequences when the observations are ambiguous. We show that the learned representation is geometrically meaningful by embedding labeled action-observation traces. Suitability for planning is demonstrated by a post-grasp manipulation example that changes the object state to multiple specified target configurations.

Many robot applications involve lifelong planning in relatively static environments e.g. assembling objects or sorting mail in an office building. In these types of scenarios, the robot performs many tasks over a long period of time. Thus, the time required for computing a motion plan becomes a significant concern, prompting the need for a fast and efficient motion planner. Since these environments remain similar in between planning requests, planning from scratch is wasteful. Recently, Experience Graphs (E-Graphs) were proposed to accelerate the planning process by reusing parts of previously computed paths to solve new motion planning queries more efficiently. This work describes a method to improve planning times with E-Graphs given changes in the environment by lazily evaluating the validity of past experiences during the planning process. We show the improvements with our method in a single-arm manipulation domain with simulations on the PR2 robot.

Asymptotically-optimal sampling-based motion planners, like RRT*, perform vast amounts of collision checking, and are hence rather slow to converge in complex problems where collision checking is relatively expensive. This paper presents two novel motion planners, Lazy-PRM* and Lazy-RRG*, that eliminate the majority of collision checks using a lazy strategy. They are sampling-based, any-time, and asymptotically complete algorithms that grow a network of feasible vertices connected by edges. Edges are not immediately checked for collision, but rather are checked only when a better path to the goal is found. This strategy avoids checking the vast majority of edges that have no chance of being on an optimal path. Experiments show that the new methods converge toward the optimum substantially faster than existing planners on rigid body path planning and robot manipulation problems.

Shape sensing techniques utilizing Fiber Bragg grating (FBG) arrays can enable real-time tracking and control of dexterous continuum manipulators (DCM) used in minimally invasive surgeries. For many surgical applications, the DCM may need to operate with much larger curvatures than what current shape sensing methods can detect. This paper proposes a novel shape sensor, which can detect a radius of curvature of 15 mm for a 35 mm long DCM. For this purpose, we used FBG sensors along with nitinol wires as the supporting substrates to form a triangular cross section. For verification, we assembled the sensor inside the wall of the DCM. Experimental results indicate that the proposed sensor can detect the DCM's curvature with an average error of 3.14%.