Roboraction.AI

Robotics

1. Stereo Vision

2. Multi View Stereo (MVS)

3. Visual Odometry

4. Visual SLAM

5. Inertial-based

6. GPS-based

7. BEV network

8. Occupancy Network

9. Data driven prediction and planning

Human Machine Interaction

1. Speech Recognition

2. Speech Synthesize

3. Natural Language Processing (NLP)

4. Chatbot

5. Face Detection

6. Face Recognition

7. Facial Landmarks Detection

8. Facial Expression/Emotion Classification

9. Hand Gesture Tracking

10. Body Pose Estimation and Tracking.

Virtual Reality and Augmented Reality

1.  Spherical View Rendering

2. Image-based Rendering

3. Depth Image-based Rendering

4. Camera Pose Estimation and Tracking

5. Image-based Relocalization

6. Volume Rendering

Autonomy

1. Image Classification and Search/Retrieval

2. Visual Object Detection and Tracking

3. Visual Scene Segmentation

4. Sensor Calibration and Fusion

5. Driving Behavior modeling and prediction

6. Pedestrian/Cyclist behavior modeling and prediction

7. HD map generation and localization

8. Simulation of traffic scenes with road network

9.  Data closed loop with smart data selection and automatic annotation

10. BEV /Occupancy perception network

Large Scale/Foundation Model

1. LLM (chatGPT, GPT-4.0);

2. Visual language model (CLIP, DALL-E);

3.  Multi-modality model (PaLM-E,  GPT-4V);

4.  Embodied AI for LLM-based agents (RT-X);

5. Fine-tuning (adapter tuning, prefix-tuning, instruct-tuning, prompt tuning);

6. Emergence (in-context learning);

7. Human preference alignment (RLHF);

8. Hauccination and interpretivity;

9.  Knowlege graph and Reasoning on graph (RoG);

10.  Search engine and Retrieval augmented generation (RAG).