Presented by: Mehran Ghafarian Tamizi

Date: Wednesday, November 5, 2025
Time: 8:30 am - 9:15 am
Place: Zoom - see below.

Zoom: https://uvic.zoom.us/j/8484626970?pwd=ZDY1bDRvZS9zU2Npa2F6aFNWR3BlQT09&omn=86170000681

Meeting ID: 848 462 6970

Password: 613295

Abstract:

Robotic motion planning remains a fundamental challenge in industrial automation, with manipulators offering a clear example of the need for real-time, collision-free, and safe trajectory generation. Traditional planners often face trade-offs among optimality, adaptability, and computational efficiency, limiting their applicability in cluttered and high-dimensional industrial environments. Furthermore, most learning-based planners suffer from poor generalization, requiring retraining when deployed in new scenes or on different robot platforms. This seminar presents two learning-based frameworks designed to address these challenges. First, we introduce the Path Planning and Collision Checking Network (PPCNet), an end-to-end neural architecture that combines a waypoint generator with a learned collision checker to enable fast, safe, and reliable planning in structured environments. PPCNet is validated in both simulated and real-world bin-picking tasks, demonstrating substantial speed-ups over classical planners while maintaining path quality. To overcome the generalization limitations of PPCNet, we propose Generalizable and Adaptive Diffusion-Guided Environment-aware Trajectory generation (GADGET), a conditional diffusion-based motion planner guided by control barrier functions. GADGET leverages voxel-based scene encoding and goal conditioning to generate safe trajectories across previously unseen environments and robotic arms without retraining. The integration of barrier-function-based guidance ensures robust collision avoidance during trajectory generation. Extensive experiments demonstrate that both frameworks achieve real-time planning performance and high success rates, with GADGET offering strong generalization to novel settings. This work highlights the potential of combining deep generative models with adaptable design to create scalable and broadly generalizable motion planners, capable of transferring across diverse environments and robot platforms with minimal modification.

Presented by: Christian Espinoza Velez

Date: Friday, November 28, 2025
Time: 8:30 am - 9:15 am
Place: Zoom - see below.

Zoom: https://uvic.zoom.us/j/82793438994?pwd=laKXbbB9a6i2EoBulHT6AVikMjbKAp.1&from=addon

Meeting ID: 827 9343 8994

Password: 611531

Abstract:

Among various motor issues, eccentricity faults pose significant challenges, leading to vibrations, reduced efficiency, and potential failure if undetected. Motor Current Signature Analysis (MCSA) is a widely used technique for diagnosing such faults, particularly in line-fed motors. However, the effectiveness of MCSA based on the modulation scheme employed in inverter-driven setup is underexplored. This thesis addresses this gap by analyzing the impact of Sinusoidal Pulse Width Modulation (SPWM) and Selective Harmonic Elimination (SHE) on diagnosing eccentricity faults in three-phase synchronous motor drives.

The study involves a three-phase, 2 kW, 208 V, 1800 rpm synchronous motor driven by an inverter, which is controlled via a Raspberry Pi Pico2 microcontroller. Using Sinusoidal PWM (SPWM) and Selective Harmonic Elimination (SHE) modulation schemes, the research examines their influence on motor current signatures, focusing on harmonic distortion and the detectability of eccentricity faults. A comprehensive experimental setup is developed to analyze both healthy and fault-induced conditions with varying eccentricity levels. Current signals are processed through Fast Fourier Transform (FFT) to extract fault-relevant spectral features and assess the sensitivity of each modulation method. The results emphasize the differences in the frequency spectra produced by pulse-width modulation systems, uncovering unexpected behaviors and trends as eccentricity increases. They also demonstrate how much easier it is to observe the magnitude and growth of specific fault frequencies when the system is connected directly to the electrical grid, compared to when it operates under pulse modulation schemes.