Career Profile
I provide freelance consulting services in Robotics and Artificial Intelligence.
I worked with Accenture from January 2022 to April 2024 as a Technical Architect Associate Manager. My role involved creating technical architectures for Robotic Systems performing tasks like pick-and-pack, material handling and inspection, and integrating them with cloud and with end-user applications. Apart from leading and guiding my team, I have assisted solution architects in creating RFP responses for solutions involving Robotics applications. Prior to this, I worked in Tata Consultancy Services (TCS) as Team Lead for Robotic Systems.
I have experience in C, C++ and Python, expertise in Robot Operating System (ROS) architecture designing, System Integration and Cloud Robotics Framework. I have successfully demonstrated many POCs throughout my career. I have developed real-life robotic applications using libraries like OpenCV, PCL for vision and tools like Gazebo for simulation. I have also trained and imparted knowledge to new recruits for working with robots.
Experiences
Working as Technical Architect for Industry X Robotics team in Accenture. Details mentioned in Projects section.
Worked as Team Lead for various Robotics use cases and applications. Details mentioned in Projects section.
Worked on IBM Sterling inventory management and order management system.
- Hardware/OS : x86-64/Windows
- Tool : IBM Sterling
Projects
The demo presented a Smart Manufacturing System concept that can learn new skills and perform new tasks. The use-case involved one component of smart manufacturing line, a pick-and-pack robot working based on orders generated from a UI. If the source (product) and destination (package) are new and unknown for the robotic system, it adapts to the new skill of object detection by generating a large amount of synthetic data using Blender and training an AI model using Google’s Vertex AI. Once the skill is ready, the model and execution pipeline are tested virtually using Gazebo. Once e2e testing is done in simulation, it can be used by the real robot for execution, which fulfils the order based on the combination of products to be packed. The system can also integrate with Google MCE and MDE to send the data for system’s various stages of execution, store it in BigQuery and use Google’s looker dashboard to analyze the KPIs to improve the overall equipment effectiveness.
Robotic integration for MARS use-case. This use-case involved integration of two robotics arms, a rover, and an IR sensor with PLC to control the conveyor for discrete manufacturing line of MARS. Based on the quality check done at different QC stations, the robotics arms were used to sort the packets either into scrap- box or move them further down the manufacturing line and finally on a rover to move it to the final drop location. All the robots, sensors, and PLC to control conveyor were integrated with the existing system using OPC-UA
This use case demonstrated the use of drones for visual inspection. A webapp was created and deployed using Azure services and a drone with edge device (running DL model) was integrated using the APIs to send the inspection results. Once the drone receives the trigger, it moves around the vehicle, sends the live feed to edge device for scratch and dent detection. The detected images were sent to cloud for end-user to visualize the inspection results.
This was a fun demo created to greet the guests coming to the lab. It involved a face recognition module to recognize the guests, greet them using a text-to-speech module and then a robotic arm with custom gripper (designed and 3D printed in-house) to hold a marker and write a welcome message with the name of guest on a canvas.
Pallet-picking Autonomous Mobile Robot for warehouse that moves pallets to their respective drop locations based on orders generated from an enterprise system. It is create map of the environment, navigate autonomously, localise itself, act on the basis of zone (user defined e.g. speed limit zone, blink zone, etc).
Autonomous Mobile Robot (AMR) which can create map of the environment, navigate autonomously, localise itself, act on the basis of zone (user defined e.g. speed limit zone, blink zone, etc) and a web based UI for end user to control and monitor. This product was selected as ‘Torchbearer of Innovation in TCS’ at TCS Innovista 2020.
Worked on integrating NAO robot with TCS chatbot KNADIA and google cloud ASR to make it respond to queries regarding TCS policies. This was presented at various innovation forums and was also showcased at IEEE Ro-MAN 2019.
A web based order fulfilment using UR5, UR10 and Turtlebot. In this the order was placed for two picking stations where two robotic manipulators were picking the object. Turtlebot carrying the box moved to picking stations one by one and the manipulators picked the items from bin as per given order and placed them in the box. Designed system atchitechture and also developed ROS node for Turtlebot navigation and coordination with the manipulators.
I was part of the team IITK-TCS and developed SMACH-ROS architecture for the system. Given a list of objects for picking, the task was to autonomously pick them from bin and place it in the respective packing box. As shown in the VIDEO it was implemented using SMACH-ROS control architecture, object detection, 3d matching for pose estimation, robot planning with dynamic updates in Octomaps for collision avoidance . The video is of pick task from the competition.
The purpose of the POC was to demonstrate robot fleet control using ROS based cloud robotics platform Rapyuta. The top level Global planner runs on a Cloud Server which provides the path information to robots. The current location of the robot is updated on the display unit available on cloud server. Obstacles can be created dynamically leading to generation of new paths, which is passed to robots.
This was the very first work assigned to me once I joined TCS Robotics Lab. Developed realtime plot using gnuplot C++ library. The purpose was to visualise the map using odometry data. Algorithm with visualisation is present at ‘prasun’ branch in the repo.
Publications
Awards
