Placement plays a crucial role in modern chip design, aiming to determine the positions of circuit blocks (macros and standard cells). Traditional data structure-centric heuristics often yield suboptimal placement prototypes, ineffectively guiding downstream mixed-size analytical placement to find the desired results for modern large-scale designs. Recent works have showcased the potential of reinforcement learning (RL) to enhance chip placement by training a policy to place macros as a board game. However, placing macros and fixing them in the earlier stages without sufficient information often incurs undesired solutions. This paper proposes a novel RL-based mixed-size placer with iteratively moving the blocks to characterize dense rewards and comprehensive layout information in each step. We further introduce a semi-concurrent moving mechanism to learn the collaborative dynamics among actions on a subset of blocks at each step. We integrate continuous action spaces to develop a deep Q network-based model for learning the semi-concurrent moving policy to derive the proposed moving strategy. Compared with the state-of-the-art methods, experimental results show that our RL-based placer achieves the best placement quality based on commonly used mixed-size placement benchmarks.

Warpage caused by the manufacturing thermal process can significantly reduce product yield in advanced packaging. As a result, numerical simulations such as finite element methods (FEMs) are often used to analyze warpage effects. However, constrained by the mesh generation and large matrix-solving requirements in finite element methods, optimizing for warpage can be time-consuming. This paper presents a fundamental physical model, training framework, and methodology for a warpage surrogate model based on DeepONets, a physics-informed operator learning framework. Experimental results show that our warpage model achieves an average speedup of 435X compared to traditional solvers while maintaining a minimal average warpage error of just 1.9%.

This paper proposes a novel high step-up DC-DC converter comprising a single switch and a three-winding coupled inductor. By using only one switch, the proposed converter simplifies control by requiring only one set of PWM signals and eliminates the need for operating at extremely high duty cycles or high turns ratios to achieve the desired gain ratio. Moreover, the converter achieves remarkable voltage gain through a voltage multiplier cell and a three-winding coupled inductor. This paper employed a 500W high step-up converter to confirm the correctness and feasibility of the proposed converter through steady-state analysis, software simulations, and hardware implementation. The measured maximum efficiency reached 95.8% when operated under 150W.

This work introduces the New Dexterity modular, dexterous, anthropomorphic, open-source, bimanual manipulation platform (OpenBMP) that is designed for research and rapid experimentation in robot grasping, dexterous manipulation, and bimanual manipulation. The platform combines adaptive and hybrid actuation systems with lockable joints, facilitating transitions between the execution of delicate and forceful tasks. Antagonistic tendon-driven elbows and inline actuator transmissions reduce the system’s inertial mass while enhancing energy efficiency and overall performance. Leveraging 3D printing and carbon fiber reinforced manufacturing of core parts, the platform is easy to replicate and highly modular. This paper presents the details of the design, the actuation principles, and the experimental validation of the efficiency of the platform with the execution of complex teleoperation and telemanipulation tasks. The designs, the electronics, and the code are open-sourced to allow replication by others.

Robot grasping and manipulation allow robots to interact with their environments and execute a plethora of complex tasks that require increased dexterity (e.g., open a door, push buttons, collect and transpose objects, etc.). Collecting data of such activities is of paramount importance as it allows roboticists to create new methods and models that will facilitate the execution of sophisticated tasks. In this paper, we propose new wearable, lightweight, low-cost human machine interfaces that improve the efficiency of the data collection process for both robotic grasping and manipulation by offering intuitive and simplified control of the employed robotic grippers and hands. In particular, two different types of interfaces are proposed: i) a handle-based forearm stabilized interface that uses a waist-linkage system to provide weight support for bulky and heavy robotic end-effectors and ii) a palm-mounted interface that can accommodate smaller and lightweight grippers and hands, offering more agility in the control and positioning of these devices. Both interfaces are equipped with appropriate sliders, joysticks, and buttons that facilitate the control of the multiple degrees of freedom of the employed end-effectors and appropriate cameras that allow for object detection, identification, and object pose estimation.

To communicate, the ~ 1.5 million Americans living with deafblindess use tactile American Sign Language (t-ASL). To provide Deafßilind (DB) individuals with a means of using their primary communication language without the use of an interpreter, we developed an assistive technology that promotes their autonomy. The TATUM (Tactile ASL Translational User Mechanism) anthropomorphic arm hand system leverages previous developments of a fingerspelling hand to sign more complex ASL words and phrases. The TATUM hand-wrist system is attached onto a 4 DOF robot arm and a human motion recognition and human to robot gesture transfer framework is used for signing recognition and replication. In particular, signing trajectories based on vision-based motion capture data from a sign demonstrator were used to control the robot's actuators. The performance of the system was evaluated through tactile based sign recognition performed by a blinded user and for its accuracy with novice, sighted users.

The ongoing global healthcare crisis has amplified the need for automation of manual tasks in several industries and service sectors. Simple household tasks such as tidying and cleaning are in high demand, with only a few robotic platforms capable of performing them due to the mobility, workspace, and dexterity requirements. This work presents ARoA, an autonomous robotic assistant that can execute complex tasks in industrial, service, and home environments. It is equipped with two lightweight, compliant, 7 degree of freedom arms and a pair of adaptive end-effectors that enable efficient execution of a wide range of tasks. Due to the linear rail based torso system that supports the arms, the ARoA offers exceptional flexibility in terms of reachable workspace. A framework for vision-based execution of tidying and cleaning tasks is also proposed and integrated in the platform. The efficiency of the ARoA platform was experimentally validated through two everyday life applications: i) picking up and tidying randomly scattered household objects and ii) cleaning of common surfaces.

Adaptive robot hands are typically created by introducing structural compliance either in their joints (e.g., implementation of flexure joints) or in their finger-pads. In this paper, we present a series of alternative uses of structural compliance for the development of simple, adaptive, compliant and/or under-actuated robot grippers and hands that can efficiently and robustly execute a variety of grasping and dexterous, in-hand manipulation tasks. The proposed designs utilize only one actuator per finger to control multiple degrees of freedom and they retain the superior grasping capabilities of the adaptive grasping mechanisms even under significant object pose or other environmental uncertainties. More specifically, in this work, we introduce, discuss, and evaluate: a) the concept of compliance adjustable motions that can be predetermined by tuning the in-series compliance of the tendon routing system and by appropriately selecting the imposed tendon loads, b) a design paradigm of pre-shaped, compliant robot fingers that adapt / conform to the object geometry and, c) a hyper-adaptive finger-pad design that maximizes the area of the contact patches between the hand and the object, maximizing also grasp stability. The proposed hands use mechanical adaptability to facilitate and simplify the efficient execution of robust grasping and dexterous, in-hand manipulation tasks by design.