Our AI research encompasses advances in computer vision, speech and audio processing, as well as data analytics. Key research themes include improved perception based on machine learning techniques, learning control policies through model-based reinforcement learning, as well as cognition and reasoning based on learned semantic representations. We apply our work to a broad range of automotive and robotics applications, as well as building and home systems.
MERL Contact: Jonathan Le Roux
Research Area: Speech & AudioBrief
Date: June 1, 2013
- The results of the 2nd 'CHiME' Speech Separation and Recognition Challenge are out! The team formed by MELCO researcher Yuuki Tachioka and MERL Speech & Audio team researchers Shinji Watanabe, Jonathan Le Roux and John Hershey obtained the best results in the continuous speech recognition task (Track 2). This very challenging task consisted in recognizing speech corrupted by highly non-stationary noises recorded in a real living room. Our proposal, which also included a simple yet extremely efficient denoising front-end, focused on investigating and developing state-of-the-art automatic speech recognition back-end techniques: feature transformation methods, as well as discriminative training methods for acoustic and language modeling. Our system significantly outperformed other participants. Our code has since been released as an improved baseline for the community to use.
MERL Contact: Michael Jones
Research Area: Machine LearningBrief
Date: June 25, 2011
- Paper from 10 years ago with the largest impact on the field: "Rapid Object Detection using a Boosted Cascade of Simple Features", originally published at Conference on Computer Vision and Pattern Recognition (CVPR 2001)
MERL Contact: William Yerazunis
Research Area: Data Analytics Date: February 1, 2010
See All Awards for MERL
Where: CEATEC'18, Makuhari Messe, Tokyo
MERL Contacts: Devesh Jha; Daniel Nikovski; Diego Romeres; Alan Sullivan; Jeroen van Baar; William Yerazunis
Research Areas: Artificial Intelligence, Computer Vision, Data Analytics, RoboticsBrief
Date: October 15, 2018 - October 19, 2018
- MERL's work on robot learning algorithms was demonstrated at CEATEC'18, Japan's largest IT and electronics exhibition and conference held annually at Makuhari Messe near Tokyo. A team of researchers from the Data Analytics Group at MERL and the Artificial Intelligence Department of the Information Technology Center (ITC) of MELCO presented an interactive demonstration of a model-based artificial intelligence algorithm that learns how to control equipment autonomously. The algorithm developed at MERL constructs models of mechanical equipment through repeated trial and error, and then learns control policies based on these models. The demonstration used a circular maze, where the objective is to drive a ball to the center of the maze by tipping and tilting the maze, a task that is difficult even for humans; approximately half of the CEATEC'18 visitors who tried to steer the ball by means of a joystick could not bring it to the center of the maze within one minute. In contrast, MERL's algorithm successfully learned how to drive the ball to the goal within ten seconds without the need for human programming. The demo was at the entrance of MELCO's booth at CEATEC'18, inviting visitors to learn more about MELCO's many other AI technologies on display, and was seen by an estimated more than 50,000 visitors over the five days of the expo.
MERL Contacts: Chiori Hori; Elizabeth Phillips
Location: Houston, Texas
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief
Date: Wednesday, September 26, 2018 - Friday, September 28, 2018
- "MERL, in partnership with Mitsubishi Electric was a Gold Sponsor of the Grace Hopper Celebration 2018 (GHC18) held in Houston, TX on September 26-28th. Presented by AnitaB.org and the Association for Computing Machinery, this is world's largest gathering of women technologists. Chiori Hori and Elizabeth Phillips from MERL, and Yoshiyuki Umei, Jared Baker and Lien Randle from MEUS, proudly represented Mitsubishi Electric at the recruiting expo, that drew over 20,000 female technologists this year.
See All News & Events for Artificial Intelligence
CD1257: Autonomous vehicles Planning and Control
The Control and Dynamical Systems (CD) group at MERL is seeking highly motivated interns at varying expertise levels to conduct research on planning and control for autonomous vehicles. The research domain includes algorithms for path planning, vehicle control, high level decision making, sensor-based navigation, driver-vehicle interaction. PhD students will be considered for algorithm development and analysis, and property proving. Master students will be considered for development and implementation in a scaled robotic test bench for autonomous vehicles. For algorithm development and analysis it is highly desirable to have deep background in one or more among: sampling-based planning methods, particle filtering, model predictive control, reachability methods, formal methods and abstractions of dynamical systems, and experience with their implementation in Matlab/Python/C++. For algorithm implementation, it is required to have working knowledge of Matlab, C++, and ROS, and it is a plus to have background in some of the above mentioned methods. The expected duration of the internship is 3-6 months with flexible start date.
CD1259: Cyberphysical Automotive Systems
The Control and Dynamical Systems (CD) group at MERL is seeking a highly motivated intern to conduct research on cyber-physical vehicle systems. The research domain includes driving assistance systems, driver-vehicle interaction, connected vehicles, and cyber-security for automotive control systems. Experience with one among particle filtering, model predictive control, constrained control, distributed control is highly desired. Working knowledge of Matlab, Simulink, C/C++, rapid prototyping systems (dSPACE), and vehicle dynamics simulators is required. Experience with CAN bus is a plus. The expected duration of the internship is 3-6 months with flexible start date.
See All Internships for Artificial Intelligence
- "Algorithms for Task Allocation in Homogeneous Swarm of Robots", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2018. ,
- "Super-resolution of Very Low-Resolution Faces from Videos", British Machine Vision Conference (BMVC), September 2018. ,
- "Recurrent Multi-frame Single Shot Detector for Video Object Detection", British Machine Vision Conference (BMVC), September 2018. ,
- "Learning Discriminative Video Representations Using Adversarial Perturbations", European Conference on Computer Vision (ECCV), September 2018. ,
- "End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction", Interspeech, September 2018. ,
- "ESPnet: End-to-End Speech Processing Toolkit", Interspeech, September 2018. ,
- "Phase Reconstruction with Learned Time-Frequency Representations for Single-Channel Speech Separation", International Workshop on Acoustic Signal Enhancement (IWAENC), September 2018. ,