TU Berlin

Robotics and Biology LaboratoryOngoing Theses

Fachgebietslogo RBO

Inhalt

zur Navigation

Ongoing Theses

Robotik

In-Hand Manipulation via Constraint Exploitation through Wrist Motions

In-hand manipulation is an act of sequencing constraint exploitations by hand and arm actuation. The constraints (static or reconfigurable) are provided by the environment or the manipulation platform itself. It is observed that humans often use wrist movements in conjunction with fingers as constraints to manipulate a wide array of objects. These wrist movements allow extrinsic resources such as gravity and inertia to be leveraged as additional sources of actuation. For the scope of this study, the role of hand actuation is limited only to producing reconfigurable constraints with no active manipulation to reduce the search space. These constraints are exploited by arm actuation for manipulation. The RBO hand 3 is used as a manipulation platform for this study as it is inherently compliant and can produce a diverse arrangement of constraints. Consequently, the goal of this study is to investigate the interplay of compliant constraint reconfiguration with extrinsic sources of actuation like gravity and inertia to generate robust manipulation behavior. mehr zu: In-Hand Manipulation via Constraint Exploitation through Wrist Motions

Easy grasping with a fixated robot

Bild

Humans interact with objects in the 3D world robustly without complicated 3D sensors like lidars. Instead they only have 2D sensors in the eyes. If compared (rather naively) to widely available camera sensors, the human retina has vastly diminished capabilities, such as resolution, refresh rate etc. How then can humans interact with the 3D world so robustly? One way is to exploit regularities in the 3D space unlocked by actively moving in specific ways. Gaze fixation is a specific movement of the body and eyes, and it can be shown to be a very useful behavior for extracting relevant 3D properties of the world. Gaze fixation is the act of looking at one object at a time under movement, just the way you would when moving about in daily life: you actively focus your attention, while tracking objects you are interested to interact with. Gaze fixation entails simultaneously sensing and acting, which is an active vision behavior. This behavior robustly finds the distance to fixated object and any immediate obstacles better than any commonly available 3D sensor. Moreover, if the camera is mounted near the robot end-effector, it allows controlling the robot in 4 DOF, instead of the general 6 DOF. This reduced DOF and extraction of robust 3D properties makes a fixating robot an ideal candidate to interact with the real world without building any sophisticated world model. mehr zu: Easy grasping with a fixated robot

Compensating the Pneumatic Actuation Noise by Using Strain and Acoustic Signals

Bild

To estimate the robot state and environment, we can use different sensors. For example, we can measure the sound inside of soft pneumatic actuators and use small changes in the sound signal to sense a wide range of actuator properties (Active Acoustic Sensor). Alternatively, strain sensors attached to the robot finger measure the deformation of the soft hull (Strain Sensor). While each sensor has shown promising results in different tasks, some disturbances lead to data corruption or loss. To achieve a robust sensor prediction, we combine multiple sensors. Additionally, this fusion might also give us more information about the pneumatic actuator state and environmental interaction and may thereby lead to a more precise contact location detection. mehr zu: Compensating the Pneumatic Actuation Noise by Using Strain and Acoustic Signals

Studying Abductive Reasoning by Playing Mastermind

Bild

Mastermind is a simple, but very clever code-breaking board game from the 70s. It is a perfect example of abductive reasoning, also called inference to the best explanation. Abduction is a method of (scientific) reasoning in which one chooses the hypothesis that best explains the available evidence. Abduction is the third type of logic inference, in addition to deductive and inductive reasoning. For example, medical doctors perform abduction when diagnosing a disease (hypothesis) given the observable symptoms (evidence). Abductive reasoning can produce false hypotheses, for example, because there might be several diseases producing similar symptoms. Doctors then go through progressively complex tests, successively decreasing the set of possible diseases matching the evidence – in principle very similar to playing Mastermind. mehr zu: Studying Abductive Reasoning by Playing Mastermind

Estimating the In-Hand Pose of Objects Using Active Acoustic Sensing and Bayesian Filtering

Bild

In-hand manipulation is an important skill for robots. While recent work in our lab has shown that even open-loop, sensorless behaviors can achieve robust results, we believe that feedback control that takes the pose of objects into account is an important stepping stone to enhance those capabilities. But what type of sensor feedback can we use to estimate the pose of objects in the hand? Another branch of research in our lab has shown that activ acoustic sensing is a promising sensing technique that can be applied to soft hands, and in this thesis we would like to explore if it can be used to estimate the pose of objects in the hand. mehr zu: Estimating the In-Hand Pose of Objects Using Active Acoustic Sensing and Bayesian Filtering

Navigation

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe