saihv commited on
Commit
2897ed9
1 Parent(s): e9c3184

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -24,19 +24,19 @@ https://github.com/microsoft/PromptCraft-Robotics
24
 
25
  **Setup**
26
 
27
- 1. Make an OpenAI ChatGPT account at chat.openai.com
28
- 2. Navigate to https://chat.openai.com/api/auth/session and copy the `accessToken`.
29
 
30
  **Usage**
31
 
32
- 1. Paste the access token in the ChatGPT Login textbox and click Login.
33
- 2. Choose a sample prompt to start with. We provide the following prompts
34
 
35
- airsim: Drone navigation scenario in the AirSim simulator.
36
- embodied_agent: Embodied agent scenario with discrete actions (left, right, forward), and perception API for object detection.
37
- embodied_agent_closed_loop: Embodied agent scenario but instead of interacting with ChatGPT normally, the user is expected to provide observations of the scene (converted into text) at every step, such as the locations of objects around.
38
- manipulation: Robot arm scenario that is equipped with a suction pump that can pick up/release objects.
39
- real_drone_sample: Drone navigation scenario for the DJI Tello drone as seen in the paper.
40
 
41
- 3. "Display Prompt" can be optionally used if you wish to see the prompt.
42
- 4. Click on Initialize, and then continue the conversation in the following chat box.
 
24
 
25
  **Setup**
26
 
27
+ 1. Make an OpenAI ChatGPT account at chat.openai.com
28
+ 2. Navigate to https://chat.openai.com/api/auth/session and copy the `accessToken`.
29
 
30
  **Usage**
31
 
32
+ 1. Paste the access token in the ChatGPT Login textbox and click Login.
33
+ 2. Choose a sample prompt to start with. We provide the following prompts
34
 
35
+ `airsim`: Drone navigation scenario in the AirSim simulator.
36
+ `embodied_agent`: Embodied agent scenario with discrete actions (left, right, forward), and perception API for object detection.
37
+ `embodied_agent_closed_loop`: Embodied agent scenario but instead of interacting with ChatGPT normally, the user is expected to provide observations of the scene (converted into text) at every step, such as the locations of objects around.
38
+ `manipulation`: Robot arm scenario that is equipped with a suction pump that can pick up/release objects.
39
+ `real_drone_sample`: Drone navigation scenario for the DJI Tello drone as seen in the paper.
40
 
41
+ 3. "Display Prompt" can be optionally used if you wish to see the prompt.
42
+ 4. Click on Initialize, and then continue the conversation in the following chat box.