MulticoreWare

Case Studies

Imaging RADAR & IMU based Static Mapping & Localization

January 23, 2023

This case study emphasizes  MulticoreWare’s role in Perception algorithm development with Automotive Radars for ADAS applications for one of our clients.

The client

The customer is a global technology company that develops sensors, sensor-based solutions for Automotive, Aerospace, Industrial, Off-road vehicles. The customer was developing autonomous navigation solutions for Off-road vehicles including its software processing pipeline.

Objective

To design an algorithm that uses Radar and IMU measurements to create a static map of the environment and localize the Ego-vehicle. For this, the static and moving objects in the environment needs to be identified. The static objects need to be represented using 3-dimensional bounding boxes. The localization process must estimate the position (in x,y,z coordinates) and orientation (roll, pitch, yaw) of the Ego-vehicle.

Constraints

Following were the constraints:

  • The algorithm had to be tailored for Radar and IMU measurements obtained in an off-road scenario
  • The Radar and IMU measurements were assumed not to be time-synchronized
  • The computational complexity of the algorithm must be minimal

Sensors

4D Imaging Radar and IMU

Technology

Simultaneous Localization & Mapping

Scenario

Large-Vehicle, Off-Road Autonomous Machines

Approach

Multicoreware oversaw the R&D from ground up, and we evaluated three approaches to solve the customer’s problem. The methods being investigated were:

  1. SLAM algorithm based on Particle filter and Kalman filter
  2. Scan matching algorithm based on Iterative Closest Point Matching
  3. Radar-Gyro fusion algorithm

Radar-Gyro fusion algorithm

  • The preferred approach by the customer was implemented
  • The approach had the best benefit in terms of accuracy vs latency trade-offs
  • RADAR –For estimating the translational movement of Ego-vehicle and static mapping
  • GYRO – For estimating the rotational movement of Ego-vehicle and its orientation
High-level architecture of Radar-Gyro fusion-based localization and mapping
Figure 1:High-level architecture of Radar-Gyro fusion-based localization and mapping

The Multicoreware advantage

MulticoreWare has a strong team with experience in ground-up R&D and knowledge of cutting-edge RADAR approaches. Our collaboration with RADAR experts from around the globe offered value to the customer by allowing us to present multiple solutions to their challenge and deliver a prototype solution that was tested live on the field. Multicoreware exceeded the customer’s expectations in this project. The client is eager to work on similar and greater challenges involving RADAR Algorithms and Perception Stack.

Outcome

With Radar-Gyro fusion algorithm, less than 1m localization error was achieved.

Share Via

Explore More

Aug 25 2023

Machine Learning and Predictive Analytics

The client is one of the leading chip manufacturers in the industry. They were trying to benchmark and enhance the multithreaded Machine Learning (ML) Inference Performance on high core count CPUs.

Read more
Nov 30 2022 Optimizing and Enhancing the Performance of an Image Processing Algorithm

Optimizing & Enhancing the Performance of an Image Processing Algorithm

This case study emphasizes our role in creating an optimized pipeline for Chroma Correction Algorithm and future enhancements for one of our clients.

Read more
Oct 19 2022 Intermediate Representation Support for ML Engine

Intermediate Representation Support for ML Engine

This case study emphasizes the role of MulticoreWare in creating and implementing a software layer to enable PyTorch backend support using the client’s existing software stack.

Read more

GET IN TOUCH