Work towards PhD degree under the supervision of Prof. Vadim Indelman
When: 24.5.2021 at 15:30
Abstract: The fundamental goal of artificial intelligence (AI) research is to allow agents and robots to autonomously plan and execute their actions. To achieve reliable and robust performance, these agents must account for real-world uncertainty. There are multiple possible sources for such uncertainty, including dynamic environments, in which unpredictable events might occur; noisy or limited sensor measurements, such as an imprecise GPS signal; and inaccurate delivery of actions. Practically, these settings require reasoning over high-dimensional probabilistic states, known as “beliefs”, representing the knowledge of the agent on the world. To decide what would be the optimal and “safest” course of action, the agent should probabilistically predict the future development of its belief, considering a set of multiple candidate actions or policies. However, such belief propagation over long horizons requires computationally demanding optimization of numerous inter-connected variables. Thus, real-time decision making under uncertainty proves to be a challenge, especially when having a limited processing power, which is often the case with mobile robots. Hence, in our work, we focused on developing methods to reduce the computational complexity of this decision making problem, while providing formal optimality guarantees. In this talk, we will present several of the novel techniques we have developed: First, we will prove and demonstrate that relying on a sparse approximation of the agent’s belief, which is represented with a high-dimensional matrix in the Gaussian case, can significantly reduce the complexity of belief propagation, while still maintaining optimality (“action consistency”); such sparsification is only utilized in the planning stage, and thus does not compromise the quality nor efficiency of the state estimation. We will then show that when the action domain is large, using bounded approximations, we can easily eliminate unfit actions, while sparing the need to exactly evaluate all the candidate actions. Finally, we will introduce PIVOT: Predictive Incremental Variable Ordering Tactic. Uniquely to this approach, we optimize the representation of the present belief (matrix) based on the predicted state development in the future, and not based on the current knowledge; this technique is not only able to reduce the complexity of decision making, but also to reduce the cost of “loop closing” when re-observing scenes during action execution. We will demonstrate the benefits of these methods in the solution of autonomous navigation and active Simultaneous Localization and Mapping (SLAM) problems, where we manage to significantly reduce computation time, without compromising the quality-of-solution.
When: 12.5.2021 at 15:30
Abstract: Robust locomotion is one of the most fundamental requirements for autonomous mobile robots. With the widespread deployment of robots in factories, warehouses, and homes, it is tempting to think that locomotion is a solved problem. However for certain robot morphologies (e.g. humanoids) and environmental conditions (e.g. narrow passages), significant challenges remain. This talk begins by introducing Grounded Simulation Learning as a way to bridge the so-called reality gap between simulators and the real world in order to enable transfer learning from simulation to a real robot (sim-to-real). It then introduces Adaptive Planner Parameter Learning as a way of leveraging human input (learning from demonstration) towards making existing robot motion planners more robust, without losing their safety properties. Grounded Simulation Learning has led to the fastest known stable walk on a widely used humanoid robot, and Adaptive Planner Parameter Learning has led to efficient learning of robust navigation policies in highly constrained spaces.
You can see the seminar Here
When: 5.5.2021 at 15:30
Abstract: Machine perception is the process of constructing a model of an embodied agent’s environment from raw sensory data. This capability is essential for mobile robots, supporting such core functions as planning, navigation, and control. However, many fundamental machine perception tasks (e.g. navigation) require the solution of a high-dimensional nonconvex estimation problem, which is computationally intractable in general. This computational complexity presents a serious obstacle to the development of practical and reliable machine perception methods suitable for real-time robotics applications. To address this challenge, in this talk we present a novel class of certifiably correct algorithms that are capable of efficiently solving generally-intractable robotic perception problems in many practical settings. In brief, these methods are based upon a (convex) semidefinite relaxation whose minimizer we prove provides an exact (globally optimal) solution to the original estimation problem under moderate measurement noise; moreover, whenever exactness obtains, it is possible to verify this fact a posteriori, thereby certifying the correctness (global optimality) of the recovered estimate. We illustrate the design of this class of methods using the fundamental problem of robotic mapping as a running example, culminating in the presentation of SE-Sync, the first practical method provably capable of recovering correct (globally optimal) map estimates. Finally, we conclude with a discussion of open questions and future research directions.
You can see the seminar Here
Work towards PhD degree under the supervision of Prof. Tal Shima
When: 5.5.2021 at 10:30
Abstract: The presented research deals with an interception scenario that consists of multiple maneuvering aircrafts and missiles defending said aircrafts from multiple incoming threats. The main objective of the research is to address the inherent coupling between aircrafts’ and defenders’ guidance and defenders’ allocation in the aforementioned multi-agent scenario, by developing novel cooperative guidance and weapon – target allocation (WTA) strategies. The talk will begin with the presentation of a problem in which the interception of the attacker by the defender is uncertain, leading to possible defenders-to-attackers re-allocations mid-flight. The research yielded guidance laws designed to deliver optimal average performance over all the possible allocation decision sequences, thus compensating for the allocation uncertainty. To ensure the feasibility of each re-allocation, we extended the aforementioned guidance laws to include a re-allocation feasibility constraint. Concretely, we enforced a constraint that all the attackers are within the defender’s seeker field of view at re-allocation time. The optimal controller for the coupled uncertain – constrained problem will be presented along with its performance analysis. Finally, we will address the problem in which the WTA scheme is not fixed and is thus subject to optimization. The investigation yielded a family of linear cooperative guidance laws and a general work frame for the development of static (i.e., before launch) WTA algorithms. The presentation of the developed WTA algorithms and their performance in comparison to an optimal WTA will conclude the talk.
When: 21.4.2021 at 15:30
Abstract: Robots today are typically confined to interact with rigid, opaque objects with known object models. However, the objects in our daily lives are often non-rigid, can be transparent or reflective, and are diverse in shape and appearance. One reason for the limitations of current methods is that computer vision and robot planning are often considered separate fields. I argue that, to enhance the capabilities of robots, we should jointly design perception and planning algorithms based on the robotics task to be performed. I will show how we can develop novel perception algorithms to assist with the tasks of manipulating cloth, manipulating novel objects, and grasping transparent and reflective objects. By thinking about the downstream task and jointly developing vision and planning algorithms, we can significantly improve our progress on difficult robots tasks.
You can see the seminar Here
Work towards MSc degree under the supervision of Assoc. Prof. Yizhar Or and Assoc. Prof. Amir Gat
When: 19.5.2021 at 14:00
Abstract: Soft robotics is an emerging field of research greatly inspired by nature, which focuses on analysis and design of robots with flexible structure that can deform and change shape and dimensions continuously. Soft robots are expected to be especially useful in in man-machine interfaces, locomotion on different terrains and through narrow spaces, robotic minimally-invasive surgery and more. This work helps to simplify the hardware needed for controlling such robots. We focus on fluid-driven elastic actuators. In those actuators the actuation is achieved by controlling the pressure or flow rate at the fluid-inlets of the structure. For complicated actuation (e.g. three-dimensional movement or locomotion) usually several separate control inlets are required. In this work, we are minimizing the amount of controlling inlets by utilizing dynamic effects of viscous flow and by using multi-stable elastic structures. Experiments were conducted in order to study the behavior of Frusta – a multi-stable structures also known as “bending straw”. This structure has many different equilibrium states. By controlling the pressure of an entrapped fluid in the frusta, we show that it is possible to switch between different states in desired order. Connecting the flow between several different frusta and using a high-viscosity liquid allowed us to present a structure where three-dimensional actuation is achieved while controlling only one inlet pressure. We also present a mathematical model and numerical simulations. Several experimental systems were built in order to verify the model and to demonstrate controlled actuation between several states.
You can see the seminar Here
Work towards PhD degree under the supervision of Assoc. Prof. Amir Degani
When: 21.2.2021 at 10:30
Abstract: The superior ability of dynamic legged locomotion to traverse rough terrain comes with the cost of fragile stability. As opposed to the commonly used closed loop control schemes, simple control schemes that only use a few basic sensors and no feedback, improve the stability of simple robots when applying a single controller. Controlling the leg angle during descent of our hopping monopod helps it keep its balance when traversing unforeseen rough terrain. Exploiting multiple controllers simultaneously, such as the free-leg length and stiffness, can further improve robustness but is often mechanically hard to implement. To overcome the mechanical complexity of designing and implementing multiple controllers, we investigate a curved leg shape that applies variable leg stiffness and free-leg length coupled with the controller, which is the leg angle during descent. We study the effect of a combination of parameters during the stance phase and show that, when traversing unknown rough terrain, it can increase robustness to perturbations in the initial horizontal velocity. We use the policy of keeping a relative height above terrain that was previously demonstrated to increase a hopper’s multistep stability. We further investigate the ability of a single leg shape to reach various relative heights with only a change in the leg angle controller. We exploit the fact that as various areas of the curved leg come in contact with the ground, they behave differently in applying physical parameters like stiffness and free-leg length. We propose a theoretical model to describe the controller coupling; present the process of obtaining the optimal coupled parameters and demonstrate its benefits by simulation. Our work also exemplifies the leg design process and validates the simulated results with experiments.
You can see the seminar Here
Work towards PhD degree under the supervision of Assoc. Prof. Yizhar Or and Assoc. Prof. Amir Gat
When: 17.2.2021 at 11:00
Abstract: Soft robotics is a field that focuses on the analysis and design of robots with flexible structures that can continuously deform and change their shape and dimensions. Possible applications of soft robotics are autonomous locomotion across rough unstructured terrain while going through narrow passages and manipulating complex obstructed environments as in robotic minimally-invasive surgery. We focus on fluid-driven soft robots where actuation is achieved by controlling the pressure at inlets of a network embedded within the elastic solid, which induces changes in the stress fields exerted by the fluid on the solid body and causes deformations in desired patterns.
In this work, we introduce two types of soft actuators. First, we obtain a general solution scheme of an elastic beam, with significant solid inertia and fluid viscosity, actuated by a pressurized viscous fluid within a serpentine-shaped embedded fluidic channel. Second, we examine leveraging viscous peeling as a mechanism to create and activate soft actuators and microfluidic devices, including complex elements such as valves. We propose a theoretical model describing the dynamics of the fluid and elastic domains, demonstrate fabrication techniques, and present experimental results validating the two cases’ theoretical model.
This work also introduces the development of two types of fluid-actuated quasi-static crawling soft robots. The first is an inchworm crawling soft robot, which exploits a common locomotion mechanism in soft robots and invertebrate creatures. We modeled inchworm crawling locomotion by approximating it with an equivalent articulated robot with elastic joints and utilizing the analysis to investigate inputs on crawling gaits’ performance. Second, we show the use of embedded pneumatic networks as a mechanism to mimic nature and generate continuous traveling waves in soft-robots by standard fabrication techniques and having only two input controls. We propose both robots’ theoretical models, which guide the design, fabrication, and optimization. Finally, we present experiments and data analysis of measurements that agree with the theoretical models.